{ "schema_version": 1, "review_window": { "start": "2026-10-13", "end": "2026-10-15" }, "review_finalized_on": "2026-10-15", "policy": "observed-catalog-and-evidence-not-capability-v1", "counts": { "catalogued": 110, "not_catalogued": 3634 }, "accepted_counts": { "not_catalogued": 14 }, "review_snapshot_modified": false, "implementation_complete": false, "papers": [ { "id": "2610.20606", "title": "Modeling and Understanding Neural Weights of Humanoid Policies with Diffusion", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20607", "title": "Hierarchical Residual Policy Learning for Real-World Mobile Manipulation with Sparse Human Guidance", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20597", "title": "Co-Evolving Acting and Forecasting for Language Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20588", "title": "Your Transformer Is Secretly Elastic", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20587", "title": "Price of Anarchy of First-Price Auctions in Agentic Markets", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20586", "title": "Continuum Attention", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20585", "title": "Learnable Hodge-Laplacian Driven Mixture of Experts for Steady-PDE Surrogates on Coarse Unstructured Meshes", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20582", "title": "Latent Compaction with Test-Time Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20578", "title": "Creating SquashFS Images to Support HPC and AI Datasets", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20576", "title": "One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20572", "title": "Recovering Reliable Supervision via Critique-Guided On-Policy Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20544", "title": "Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20538", "title": "PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20534", "title": "Revisiting Simple Baselines for Relational Deep Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20533", "title": "Generative Representation Learning for Scalable Latent Tokenization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20532", "title": "ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20525", "title": "The Physics Is the Network: Fast, Training-Free Neural Emulation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20516", "title": "VASPO: Self-Distillation with Privileged Value Estimation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20514", "title": "Bayesian Learning to Select Fair Classifiers", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20512", "title": "A Two-Level Clinical Novelty Prioritization Framework for Disease Trajectories Discovered from Longitudinal Electronic Health Records", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20509", "title": "VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20502", "title": "Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20497", "title": "Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20486", "title": "Average-Reward Policy Identification from a Single Continuing Trajectory", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20483", "title": "Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20479", "title": "Lost in Translation: Why Lower Bias Scores Don't Mean Fairer Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20473", "title": "SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20463", "title": "Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20462", "title": "Learning by Examples: Power Grid Steady State Analysis with a Tabular Foundation Model", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20456", "title": "The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20450", "title": "What Does Disagreement Mean? A Semantic Identifiability Frontier for Pairwise Preference Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20439", "title": "The Accuracy Well: Nonmonotone Accuracy Dynamics at Vanishing Initialization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20426", "title": "Continual Learning for Reliable In-Sequence Molecular Communication", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20418", "title": "OrionMoE-v1.0: A Mixture-of-Experts Foundation Model for Tabular In-Context Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20416", "title": "Tracking a Small Set of Experts in Online Convex Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20415", "title": "One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20413", "title": "When Does Momentum Help in Reinforcement Learning with Verifiable Rewards?", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20409", "title": "Hyperspherical Contrastive Representations Unlock Planning and Exploration", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20402", "title": "Posterior Frequencies and the Cost of Not Fitting: A Correction to a Memorization Lower Bound", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20401", "title": "Training Language Models to Fail Gracefully", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20400", "title": "HRTF Upsampling and Personalization via Neural Operators", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20399", "title": "Cortex: Consolidating Context into Parametric Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20396", "title": "From Human Corrections to Learned Segmentations: A Critical Mathematical Review of Information, Learning, and Human Effort", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20392", "title": "FOLD: Position-Free Far Memory with Local Order for Long-Context Speculative Decoding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20375", "title": "Hypothesis Selection via Weighted Medians", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20369", "title": "ReAl: Refine neural operators via aligning dynamical flow", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20363", "title": "Fractional is Better: Learnable Derivative Orders in Neural Operator Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20353", "title": "Beyond Expert Rankings: Contrast Calibration for Mixed-Precision MoE Quantization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20350", "title": "Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20349", "title": "NeuroDETR: Multiscale Discrete Spatiotemporal Tokenization for Asynchronous EEG Event Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20347", "title": "Non-asymptotic Convergence of Average-reward Q-learning with Options", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20342", "title": "When Does Task-Aware Imputation Matter? An Analysis of Robustness Under Train-Test Mismatch", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20337", "title": "Training Dynamics of Transformers on Unbounded Inputs: Attention Learning Can Lag Output Layer Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20331", "title": "Are We Overthinking One-Step Generation?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20326", "title": "Comparative Evaluation of Deep-Learning based DoA Estimators for Real-Time ISAC Beamforming", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20318", "title": "Efficient Test-Time Adaptation For Robot Policies", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20305", "title": "Extreme-Scale Super-Resolution of Homogeneous Turbulence from a Single Realization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20303", "title": "SpectrumQuant: Spectrum Alignment for LLM Quantization", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20294", "title": "MMLA-RSI: Recursive Self-Improvement through RTT and RTMA", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20293", "title": "CASI: Credit Assignment via Set Intervention for Agentic Retrieval", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "casi", "detail_path": "reproductions/2610.20293-casi/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.20288", "title": "Predicting Unseen Scientific Interactions: Conditional Flow Models Hallucinate Non-Additive Effects", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20286", "title": "From Plato to Aristotle: Toward a General Theory of Representation Hypotheses", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20277", "title": "TANGO: RNA Topology and Geometry Co-Design", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20274", "title": "Resolution Allocation with Learnable Resizing and Spectral Filter Parameterization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20269", "title": "FlowSep-RF: Rectified Flow Matching for Single-Channel Radio-Frequency Signal Separation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20264", "title": "FUSE: Fairness-aware Update Screening against Byzantine Exploitation in $q$-Fair Federated Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20261", "title": "Harness Policy Distillation: Aligning Agent Policies with Runtime Semantics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20256", "title": "Long-Horizon RL Needs Muon", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20252", "title": "Adversarial Reinforcement Learning for Robust Planetary Landing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20251", "title": "Contrastive uncertainty learning for robust multi-structure segmentation in lower-pelvic MR", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20247", "title": "Scaling Multilingual Mixture-of-Experts: How Language Coverage Changes Capacity and Compute Allocation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20243", "title": "Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20238", "title": "MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20229", "title": "The minimal width of neural networks and immersions of real projective space", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20218", "title": "Mixed Poisson diffusion models and application to posterior sampling", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20217", "title": "Continual pretraining Prostate MRI ViT Encoder for task alignment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20209", "title": "HGRP: Heterogeneous Graph Neural Network for Routability Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20203", "title": "Investigating Behavior Cloning from Few Demonstrations for Autonomous Driving based on Bird's-Eye View in Simulated Cities", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20191", "title": "HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20187", "title": "Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20179", "title": "Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20174", "title": "RM-OPD: On-Policy Distillation for Generative Reward Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20170", "title": "Optimizing Sparse Boolean Rule Networks using Mixed Integer Linear Programming", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20162", "title": "Gap Detection: Mitigating Homogenization through Demand and Defensibility", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20138", "title": "In-Context Batch Black-box Optimization via Flow Matching", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20136", "title": "Seeing at the Edge: Energy Characterization of Vision-Language Model Inference on Edge Platforms", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20122", "title": "XViewRank: Overlap-Conditioned Score Fusion for LLM-Augmented Sparse Retrieval", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20120", "title": "A Bregman Proximal Viewpoint on Neural Operators", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20117", "title": "KANLab: TensorFlow Playground for Kolmogorov-Arnold Networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20112", "title": "From Spectral to Frobenius: When Muon Loses Its Spectral Implicit Bias", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20108", "title": "Exhaustive Canonical Skeletons Generation: A Formal Dataset for Decomposable Symbolic Regression", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20104", "title": "What Do Foundation Models for Market Microstructure Learn? A Controlled Study with Synthetic Limit Order Books", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20075", "title": "A Large-Dimensional Analysis of Least-Squares Federated Learning via Generalized Total Variation Minimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20071", "title": "Rethinking Prediction Horizons: Decoupling Model Queries from State Updates in Few-Step MeanFlow", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20069", "title": "Trainable at Depth, Solvable at Small Size: What the Loss Surface of a Polynomial Activation Dictates for Designing, Initializing and Training Networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20053", "title": "GBTSVR: Twin Support Vector Regression via Granular Ball Computing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20048", "title": "Reading the Neighborhood: Text-Attentive Graph Reranking for Automated Subject Indexing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20041", "title": "Sequential Learning-Based Physics-Informed Neural Network Modeling for Parameter Estimation on a Power Converter", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20035", "title": "Weighted Adjoint Matching: Finetuning Flow Matching Models with Time-Dependent Control Cost", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20014", "title": "On the Convergence of Semi-Gradient TD: A Mean Field Perspective", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20012", "title": "ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20009", "title": "Outperforming 1000 Euclidean Layers With Hyperbolic Goal-Conditioned RL", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20007", "title": "Minimax estimation of the pseudo-spectral gap of continuous Markov chains, with applications to empirical concentration bounds", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20004", "title": "Provable Transformer Context Compression for In-Context Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19997", "title": "Empirical Boundaries of Reservoir Computing for Few-Shot Sequence Pattern Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19975", "title": "LatentLoop: Scaling Looped MoE Models with Asymmetric Compute Allocation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19968", "title": "Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19966", "title": "Choosing the Number of Attention Heads from Intrinsic Dimension: A Small-Scale Study", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19951", "title": "AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19946", "title": "Learning Graph Energies for Finite-Time Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19942", "title": "MorphingNet: Symbolic Regression Where the Network Is the Formula", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19931", "title": "SAM3RL: Memory Control via Reinforcement Learning for Visual Object Tracking", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19925", "title": "Convergence Rates of Gaussian Process Thompson Sampling for Efficient Global Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19920", "title": "MolHop: Scaffold-Hopping Molecular Design with Agentic Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19919", "title": "Beyond DFT electronic band structures via dual-space orbital learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19911", "title": "CARD: Closing the Teacher-Student Loop for Adversarial Robustness Distillation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19910", "title": "When Non-Adversarial Noise Hurts Learning: Benchmarking Skill Self-Evolution in Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19901", "title": "Multimodal Medical Image Parsing with Task-Specific Low-Rank Adapters", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19899", "title": "Universal Sample-Based Embeddings of Higher-Order Objects", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19893", "title": "Few-Shot Adaptation for Anomalous Sound Detection at Low False-Positive Rate", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19892", "title": "On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19883", "title": "Occupancy Modeling via Drifting: One-Step Generation Enables Direct Policy Extraction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19878", "title": "Neural Wasserstein Splines: Representation-Invariant Second-Order Priors for Trajectory Inference", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19876", "title": "SPARS: A Stability-Plasticity-Aware Region Selection Framework for Continual Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19868", "title": "Explorer-Zero: Improving Self-Play for Long-Horizon Tasks with Decomposable Verifiable Rewards", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19861", "title": "On the Optimisation Landscape of Overparameterised Weighted MMD", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19860", "title": "Text-Informed Training Data Filtering for Enhanced Virtual Flow Meter Performance", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19855", "title": "Energy Consumption Analysis of Discrete Diffusion and Autoregressive Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19844", "title": "Memory-Efficient Subspace Optimization with Residual Correction: From Momentum SGD to Muon", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "smrc-pmrc", "detail_path": "reproductions/2610.19844-smrc-pmrc/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/smrc-pmrc-a100-20261015.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.19832", "title": "Rent-Seeking Language Models: Reward Models Set the Prices, Frequent Audits Curb the Rent", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19831", "title": "CTIA-ODE: Continuous-Time Inter-Variable Attention for Long-Term Time Series Forecasting", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19827", "title": "MAPLE: A Multi-Axis Parametric Knowledge Extraction Lens for LLM Evaluation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19822", "title": "JointServe: Serving Multi-Model Agents on Memory-Constrained GPUs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19814", "title": "When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19813", "title": "VaryST: Generalizable Spatio-Temporal Forecasting Beyond the Closed-World Setting", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19811", "title": "Calibration and Risk-Budgeted Decisions with System One Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19810", "title": "ReproBAIT: Can coding agents build their own biological AI tools?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19804", "title": "Efficient contextual partial monitoring with general function approximation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19802", "title": "Asymptotically Exact Negative Guidance of Diffusion Models via Positive-Unlabeled Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19795", "title": "StateCraft: Augmenting Video World Models with Abstract-State Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19789", "title": "More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19783", "title": "Reinforcement Learning via Advantage Guidance", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19782", "title": "Learning Who Benefits Most: Multi-Treatment Causal Ranking for Population Health Stratification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19781", "title": "SNACK: A Sequential Notation Framework for Probabilistic Graph Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19773", "title": "From Global to Tail Convergence: Dynamics of $α$-Stable Score-Based Generative Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19769", "title": "When Does the Dependency Graph Help Code-to-Architecture Mapping?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19768", "title": "Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19766", "title": "Analyzing and Mitigating Poisoning Attacks on Flow-Based Intrusion Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19761", "title": "CAST: History-Adaptive Spectral Clipping for LLM Pretraining", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19743", "title": "Discriminative Score Function: Turning Pretrained Models into Functional Generative Priors", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19738", "title": "ProtModernBERT: Compute-Efficient Protein Language Modeling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19731", "title": "What Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19725", "title": "TIMERSI: Towards Self-Improved Agentic Deployment for Time-Series Foundation Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19721", "title": "Articulation Upper Bounds for Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19719", "title": "Learning Individual Scientific Taste with Privileged Hindsight Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19712", "title": "New Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19700", "title": "ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19692", "title": "Annealed Lévy Diffusion via Gaussian Surrogate Reverse Dynamics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19687", "title": "Function-Space Temporal Self-Distillation for Policy Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19685", "title": "Beyond Distribution Matching: Selective Margin Preservation for Supervised Fine-Tuning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19683", "title": "Enhancing Latent World Models with Associative Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19679", "title": "MCAIR: Monitoring and Correcting Agent Unfaithfulness via Internal Representations", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19654", "title": "HACHIMI-II: From Role-Play to Learner Behavior Modeling for Faithful Student Simulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19652", "title": "On Global Joint Lower Bounds in Zeroth-Order Nonconvex Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19642", "title": "Model What Matters: Decision-Guided Selective World Modeling for Language Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19640", "title": "Synthetic reaction data from transformation rules for graph-to-sequence pretraining in biodegradation pathway prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19636", "title": "Sparse Autoencoders Are a Shared Coordinate System for Symbolic Matching", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19630", "title": "Risk-Controlled DFT Selection for Machine-Learned Interatomic Potentials", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19628", "title": "Self-Conditioning Enables Deep Sequential Reasoning in Flow Matching", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19625", "title": "DAGFormer: Global Topology Prediction for Transformer Cross-Layer Connections", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19614", "title": "Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19608", "title": "Twenty Days Later: A Pre-Registered Test of History-Based Forecasts of Brand Mentions in Gemini Answers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19607", "title": "A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19605", "title": "PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "pn-mix", "detail_path": "reproductions/2610.19605-pn-mix/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/pn-mix-a100-20261015.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.19603", "title": "Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19592", "title": "InstructPro2: Natural Language and Biological Grounding Guided De Novo Protein Design", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19591", "title": "L3M: A Verifiable Harness and Runtime for Self-Extending and Self-Improving Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19588", "title": "Projected Wasserstein-Fisher-Rao Flows for Hawkes Background-Intensity Estimation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19583", "title": "Who's Behind the Text? Robust Model Authorship Attribution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19578", "title": "Bridging the Topological Divide: Dual-Branch Graph Distillation with Semantic Priors for Robust Cold-Start Recommendation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19576", "title": "Learning Across Temporal Graph Representation Silos", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19573", "title": "On Inherent Privacy of Posterior Sampling: A Unified Rényi-Divergence Framework", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19570", "title": "Geometric Kernel Diversity: An Axiomatic Diversity Measure in Euclidean Space", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19568", "title": "INTACT: Inducing Latent Reasoning on a Frozen Backbone", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19557", "title": "TEX-MEX: Similarity-Guided Temporal Contrastive Learning for Time Series", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19556", "title": "Evidence-Anchored Overdose Death Prediction from Death Investigation Reports", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19552", "title": "Test-Time Forecasting: Recurrent Depth Enables In-Context Dynamics Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19543", "title": "Noisy-Label Calibration with Multiple Unreliable Labels", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19539", "title": "Two-stage Residual Learning for Modelling Strength-Informed Optimisation of Thermal Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19536", "title": "Typed Decision Models on Tabular Data", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19532", "title": "A Unified Response Framework for Questions and Tutoring Dialogues", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19528", "title": "Retrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19525", "title": "Diagnosing and Correcting Reward Hacking in Verifiable Instruction Following", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19524", "title": "HankelKANet: Lightweight Path Loss Estimation via Physics-Inspired Hankel Convolution", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19513", "title": "High-Probability Regret Bounds for Feel-Good Thompson Sampling", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19508", "title": "CktHGVAE: A Symmetric Design/State Heterogeneous Graph Variational Autoencoder for Transistor-level Analog/Mixed-signal Circuit Design and Analysis", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19505", "title": "SKG: A Law-Induced Engine from Inference to Induction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19498", "title": "What You Sign Is Not What You Run: The Verifiability Gap in Quantized LLM Supply Chains", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19490", "title": "Digital Self-Interference Cancellation for In-Band Full-Duplex Systems Based on Transformer Neural Operators", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19484", "title": "State-Matched Sequence Conformal Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19457", "title": "MIPS: Mitigating Mode Collapse in Reinforcement Learning for Large Outcome Spaces", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19454", "title": "AdCoEvo: A Co-Evolving Multi-Agent Advertising Delivery System", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19444", "title": "Large-Step Last-Iterate Convergence of Random-Reshuffling Stochastic Gradient Descent", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19439", "title": "Progress-Aware Distillation for Mitigating Stagnation in Small Language Model Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19436", "title": "Learning to Select Features with Manifold Deep Unfolding PCA", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19429", "title": "Comprehensive Comparisons of Reinforcement Learning Algorithms in Autonomous Driving", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19411", "title": "W-JEPA: Wavelet Joint-Embedding Predictive Architecture for Wearable Activity Recognition", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19405", "title": "Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19404", "title": "ActMOF: Mapping Reticular Synthesis through Active Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19401", "title": "Train to Stitch: Topology-Preserving Regularization for Interoperable Representations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19398", "title": "RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19394", "title": "Selective Next-Location Prediction with MetaModelSelect: A Lightweight Post-Hoc Confidence Metamodel", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19391", "title": "Fully sequential Gaussian process regression for preference learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19385", "title": "RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19378", "title": "Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19375", "title": "One-Step Prediction Fidelity Is a Poor Proxy for Planning Performance in JEPA World Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "jepa-prediction-planning", "detail_path": "foundation-models/2610.19375-jepa-prediction-planning/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.19372", "title": "Policy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19369", "title": "The Impact of Detector Architecture, Model Scale, and Scene Density on Multi-Pedestrian Tracking", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19364", "title": "Dynamic Graph World Modelling: Learning Future Dynamics from Temporal Context", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19362", "title": "Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19359", "title": "Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19358", "title": "Asymptotic Behavior of Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19352", "title": "BFHD: Bidirectional Feature Harmonization Decomposition for Heterogeneous Clinical Assessments", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19349", "title": "Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19347", "title": "Integrated Novelty Detection Systems: From Sensor Networks to Multi-Novelty Computer Vision", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19344", "title": "Target-Token Asymmetry Can Masquerade As Depth Specialization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19343", "title": "Counterfactual Gate-Support Decomposition: Separating Selection from Redistribution in Training-Data Filtering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19324", "title": "Why don't Graph Transformers attend to the same token?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19323", "title": "TopicMerge: A Divide and Conquer Approach to Topic Modeling", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19315", "title": "Historical-Feature Residual Adaptation for Sequential Screening", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19306", "title": "Did the LLM Answer the Question? A Semantic Reconstruction Game for Jailbreak Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19302", "title": "DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19298", "title": "Verifier-Grounded Agentic RL for Provably Correct Code", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19281", "title": "Exact Scaling Laws for a Random-Features Bigram Model", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19279", "title": "Dimension-Free Scaling Laws for Size Generalization: An Exponential Separation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19271", "title": "Outcome-Routed Distillation and Reinforcement Learning for Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19270", "title": "Exploring Interpretability in Deep Learning-Based Forest Classification - Separating Similar Forest Classes using Sentinel-2 Time Series", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19254", "title": "Beyond Time Induction: Structured Conditional Neural Solvers for Parametric Stochastic-Volatility Pricing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19252", "title": "Multi-Sensitive Distributional Fairness: Joint Wasserstein Audits and Shapley Allocation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19246", "title": "Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19240", "title": "FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19238", "title": "LLMs program using Reusable and Composable Abstract Representations", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19235", "title": "From Detection To Anticipation: Continuous Onset Forecasting For Stuttered Speech", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19232", "title": "Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19220", "title": "Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19215", "title": "Narrowing the Collaboration Gap, Probably", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19211", "title": "Generalizing Identifiability Results in Causal Discovery from Complete Data to Missing Data Settings", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19198", "title": "Embedding Geometry Shapes LLM Routing: Tracing Failure Modes and Improving Generalization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19191", "title": "FireGraphNet: Sub-daily wildfire spread prediction with directed graph neural networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19189", "title": "Adaptive Computation with Conformal Certification", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19187", "title": "Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19185", "title": "How to Evaluate When You Don't Know How to Evaluate? Choosing Reliable Setups for Base Language Model Benchmarking", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19179", "title": "Learning in Strategic Queuing with Geometric Recharge: From Bandits to Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19178", "title": "Diagnosing Low-Confidence Patient Profiles via Localized Harmful Covariate Shift Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19159", "title": "Into the Unknown: Benchmarking AI agents on open scientific research problems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19145", "title": "Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19142", "title": "Towards Training and Inference of Graph Neural Networks in Graph Databases", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19139", "title": "Online Tokenization with Optimal Delay in Linear Time", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19138", "title": "MA-Bench: Measuring Operational Planning in Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19135", "title": "Student Copula Markov Networks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19133", "title": "TRACER: Trace-Regularized Training Against Indirect Prompt Injection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19129", "title": "Imagining Goals with Geometric Horizon Models for Policy Generalization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19123", "title": "PairIT: Autoregressive Transformers for Low-Data Molecule Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19121", "title": "Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19114", "title": "Genesis Steering: Better Activation Steering Through Training Data", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19113", "title": "From Copying to Composition: How Language Models Develop In-Context Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19104", "title": "Neural Supervised Clustering for Learning Individualized Treatment Rules with Many Treatments", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19103", "title": "Contextual Credit Policy Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19095", "title": "Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19084", "title": "Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19080", "title": "Backpropagating Verifier Rewards Through Continuous Flow Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19074", "title": "Theoretical and Practical Advances in Hierarchical Bayesian Deep Learning Methodology", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19068", "title": "Plan or Retrieve First? A Scale Study of Tool Discovery Architectures", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19065", "title": "Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19064", "title": "How Inner Optimizers Shape Replica Scaling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19058", "title": "Conformalized Physics-Informed Weak Regression for Parameter Estimation in Epidemic Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19053", "title": "Deep Generative Models for Phylogenetic Inference with Complex Evolutionary Processes", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19051", "title": "Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19046", "title": "What Information Buys in Active Inference", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19043", "title": "Graph Coarsening Enables Escaping Local Optima in Compute-Constrained Nonconvex MAX-CUT", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19042", "title": "Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19041", "title": "Tracing Morphology, Semantics, and Divergence in Language Acquisition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19038", "title": "Lag: A Mean-Field Optimal Policy for Online Assignment with Reusable Resources", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19035", "title": "Who Should We Listen to More? Welfare-Aware Preference Acquisition for Pluralistic Alignment", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19033", "title": "How Many Ranks Does a Token Need? A Noise-Floor Squelch for Rank-One LoRA Experts", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19027", "title": "Optimization for One, Feasibility for Most: Decoupling Optimization from Feasibility in Chance-Constrained Programs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19025", "title": "How Far Can Coding Agents Go in Visual Generation?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19020", "title": "Discrete Diffusion Models are Minimax Optimal Under Sparsity", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19016", "title": "IR-PRM+ with Previous-Utility Prediction: Constant Regret and Best-Iterate Convergence", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19015", "title": "Scaling Cheap Synthetic Pretraining Improves Indoor Radio-Map Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19013", "title": "Data Density Scaling Laws for Image Self-Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19011", "title": "PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18990", "title": "Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18835", "title": "RoboSimStudio: An Interactive Toolkit for Human and Agent Rapid Real2Sim of Robot Manipulation Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18949", "title": "Virtual-Alloy Physics-Aware Semantic System for extrapolative prediction of perovskite solar cells", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18651", "title": "Does Pretraining Teach Chemical Language Models Chemistry?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18948", "title": "Limits of Statistical Assurance for Embodied and Agentic AI under Adaptive Adversaries", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18946", "title": "Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18945", "title": "Semi-Amortized Bayesian Inference with Reusable Local Posteriors", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18465", "title": "How Safe Is ChatGPT Health Advice? Evidence from Real User Conversations in Four Global South Countries", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18462", "title": "Readout Scaling Shapes Sparse Feature Recovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18434", "title": "Principled Design of Expected Improvement for Continuous Simulation Optimization", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18939", "title": "Wong--Zakai Convergence and FNO Learning for Stochastic Volterra Equations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18309", "title": "Prompt or Policy? Optimizing Physician Slate Presentations with LLM User Simulators", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18308", "title": "SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18938", "title": "Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18935", "title": "Delay Complexity Dimension: Learning with Delayed and Censored Labels", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18934", "title": "An Initial Study of Physiological Markers for Deepfake Speech Detection", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18933", "title": "The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18088", "title": "ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18054", "title": "Privacy-Preserving GNN Inference on Financial Transaction Graphs via Homomorphic Encryption", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17986", "title": "Web Scale on a Budget: Tail-Aware Retrieval Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17895", "title": "Interaction-as-a-Judge", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17867", "title": "RT-J: Large-Scale Pretraining of Relational Transformers for Context-Efficient Predictions", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17856", "title": "MMTA: Benchmarking Multimodal Temporal Analysis with Time Series, Text, and Vision", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17841", "title": "FASHION-RQ: Mining Hierarchical Semantic Structure for Automated Evaluation of Fashion Retrieval", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17823", "title": "Mitigating Popularity Bias in Sequential Recommendations with Sparse Prior-Regularized Objective", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17771", "title": "Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17747", "title": "Auditing Failure Attribution: Label Predictability and Judge Behavior", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17623", "title": "RELAY: Selective Self-Distillation with Adaptive Hand-off for Rubric-Based Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18924", "title": "TorchSpin: Differentiable Electron Paramagnetic Resonance Simulation in PyTorch", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17467", "title": "Computed, not Memorized: Bit-Factorized Identifiers for Efficient Generative Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17407", "title": "Cross-View Time-Frequency Diffusion for Extreme-Aware Time-Series Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17368", "title": "HASTE: Hierarchical and Attribute-aware Supervision for Generative Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18917", "title": "Popularity Trajectories and Mixing Patterns of Urban Venues in Two European Cities", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16979", "title": "WeGR: Unified Generative Retrieval for Industrial Search Systems in WeChat", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "wegr", "detail_path": "reproductions/2610.16979-wegr/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.16948", "title": "Learning to Design Convex Relaxations for Nonconvex Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16689", "title": "EHR-Bench: A Chinese Multi-Task Benchmark for Recruitment AI", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16597", "title": "DEFlow: Deep Equilibrium Flow Maximum-Entropy Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16596", "title": "Towards Modality-Agnostic Seizure Classification: A Unified Deep Learning Framework for Heterogeneous EEG and Intracranial EEG Signals", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16440", "title": "ARMED: Adaptive Retrieval-Augmented Medication Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16229", "title": "Tackling the Modality Inhibitance Effect with Wavelet-based Modality Integration in Multi-modal Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16132", "title": "UniSGR-V2: Stepwise Target-Side Feature Anticipation and Crossing for Generative Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "unisgr-v2", "detail_path": "reproductions/2610.16132-unisgr-v2/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.16038", "title": "OT-FlowRec: Optimal Transport-Guided Multi-Bridge Flow for Multimodal Sequential Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18904", "title": "Distinguishing Process Change, Instrument Fault and Data-Path Corruption in Streaming Telemetry: A Reference Implementation and Benchmark", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15864", "title": "Personalized LLM Recommendation with Semantic IDs: Autoregressive Beam Search vs. Multi-Token Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15832", "title": "Local Citation Recommendation Without Graph Signals", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15778", "title": "Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15696", "title": "DRanker: A Transformer-Based Multi-Task Ranking Model for the Disney+ Homepage", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15669", "title": "ProtoPur: Prototype-Purity Pseudo-Labeling for Weakly Supervised Instance Learning in Pathology", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15661", "title": "Feedback as an Interface: Controlling Form and Detail in LLM Translation Refinement", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15564", "title": "UNISON: A Unified Framework for Learning from Scored Bags", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15523", "title": "Rethinking Evidence Modeling: Context-Coupled Graph Learning for Multimodal Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15505", "title": "Federated Semantic Residuals for Multimodal Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15484", "title": "Toward Explainability in Multimodal Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15322", "title": "SuperAI: Merging Capabilities Across Heterogeneous Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15020", "title": "PATTERN Can Be Solved from Memory: Generator-Aware Baselines for Synthetic Node Classification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14959", "title": "AlphaRLM: Aligning Language Models for Literature-Grounded Symbolic Factor Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14816", "title": "Data Curation and Model Souping: Unlocking Qwen3-0.6B for MS MARCO Passage Ranking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14757", "title": "Rethinking Opinion Measurement Interfaces for Human-in-the-Loop Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14709", "title": "Vela: User Behavior as Supervision Sparks LLM Intelligence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14579", "title": "Fine-Tuning Strategy, Not Just Data: A Statistically Rigorous Audit of Gender and Stereotypical Bias in Embedding Models for HR Recommendation Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14567", "title": "Strong Gaussian Approximation of Constant Learning Rate SGD: Bias and Trajectory Inference", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14550", "title": "LLM-based User-Product Relevance Evaluation for Dynamic Product Advertising", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "snap-dpa-relevance", "detail_path": "reproductions/2610.14550-snap-dpa-relevance/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.14474", "title": "RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14394", "title": "Understanding and Mitigating Training Instability in Large-Scale Recommender Systems: A Cascade Perspective", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14350", "title": "Natural Code Transformation Confuses Agents in Vulnerability Analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14315", "title": "MvFFN: Multi-view Floor plan Feed-forward Network for Unposed Wide-Baseline Panorama Layout Reconstruction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13935", "title": "Hide and Seek: HIDE Concepts to SEEK explanations for black box models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13928", "title": "AI Models Can Provably Hide Arbitrary Capabilities", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13806", "title": "FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "forte", "detail_path": "reproductions/2610.13806-forte/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.13504", "title": "Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13398", "title": "Towards the Roof of the World: NLP Progress in Tibetan Languages", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13082", "title": "Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13057", "title": "CoBe: A Benchmark For Conversational Counterfactual Text Editing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12848", "title": "Reinforcement Learning via Fixed-point Flow Matching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18890", "title": "AI-Driven, Timing-Aware Power Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12393", "title": "HRIL: Learning Multimodal Synergy via Higher-Order Tensor Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18889", "title": "Bayesian Causal Forests for Zero-Inflated Continuous Outcomes", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11896", "title": "Automated Assembly Instruction Generation from CAD Models Using Grounded Large Language Models: A Human-in-the-Loop Framework", "review_decision": "archived_source_exception", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11501", "title": "Beyond Sequences: Distilling Structured Decision Memory for LLM Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11152", "title": "Do LLMs Learn from Rewards in Context? : Rethinking the role of reward in In-Context RL", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11030", "title": "NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10920", "title": "Language Models for Page-Level Layout Decisions in E-commerce Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10639", "title": "Visible Reasoning Is Not a Universal Optimizer: Persona- and Thinking-Dependent Effects in Analytics Code Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10124", "title": "Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability Competition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10080", "title": "Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10076", "title": "Towards Calibrated Probabilistic Forecasts for Events of Interest via Outcome-Conditional Recalibration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09906", "title": "Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09369", "title": "Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09070", "title": "Covariate-dependent Joint Modeling of Multivariate Ordinal Preferences and Its Connections with Comparison Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08652", "title": "Steering Diffusion Models to Rare Events with Sequential Monte Carlo", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18886", "title": "Physics-Guided Multi-Fidelity Surrogate Modeling for Natural Supercavity Geometry of an Axisymmetric Conical Cavitator", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08407", "title": "Seeing the Context: Enhancing Recommender Systems with Image-Derived Contextual Signals", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08245", "title": "Aligning Performance with Contribution: Towards Contribution-Aware Fair Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08232", "title": "Behavior-Mining, Generative Conversations, and Collaborative Advisory: the Future of Travel and Tourism Recommender Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08159", "title": "Making COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08136", "title": "Adapting Generative Recommenders for Multi-Turn Interaction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08129", "title": "Do LLMs Act on What They Know? From Partner Representations to Cooperative Actions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08078", "title": "ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08077", "title": "Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07853", "title": "Lost in the bf16 Cast: Exporting Ternary Language Models Can Revert Most Low-Learning-Rate Code Changes", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07810", "title": "SIFT: Search Intent-to-Filter Transformer for Multi-Task Personalized Filter Ranking at Airbnb", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07761", "title": "Contrastive Learning for Aspect Representation towards Explainable Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07402", "title": "Rethinking Semantic ID Construction for Generative Recommendation: SimHash with Parallel Decoding and Semantic Alignment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06751", "title": "MatrixFormer: A Foundation Model for Matrix Completion", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06703", "title": "Reading the Mood: Emotion-Guided Book-to-Music Recommendation via CGANs and LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06590", "title": "SPRIG: Semantic-ID-enhanced Paths for Knowledge Graph-based Generative Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07105", "title": "Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06450", "title": "EMG-FM-Bench: A Comprehensive Benchmark for Foundation Model Transfer and Adaptation on Electromyography", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06050", "title": "MATE: Adaptive Long- and Short-Term User Memory for LLM-Based Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05998", "title": "Langevin Flow Maps: Efficient Molecular Dynamics and Transition Path Sampling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05994", "title": "How (and How Not) to Use Data Augmentation in VLA Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05949", "title": "Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05787", "title": "Constraint-Aware Conversational Job Recommendation in Code-Mixed Low-Resource Settings", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05670", "title": "Generate What You Can Trust: Content Credibility in Generative Recommenders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05559", "title": "Cut Binary Cross Entropy: Efficient Large-Vocabulary Loss and Gradient Kernels for Sequential Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05532", "title": "DelegationBench: Measuring When AI Agents Should Ask Before Acting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05501", "title": "Logic-Logit: A Logic-Based Approach to Choice Modeling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05220", "title": "Ranking Bandits for Carousel Interfaces with Observable Browsing Depth", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04444", "title": "Causally Fair Generation with Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04302", "title": "From Valid to Useful: Post-Verification Acquisition for Recursive Self-Improving Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03923", "title": "Learning Robust Personalized Prompts for LLM-Driven Sequential Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03709", "title": "From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message Passing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03225", "title": "The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03201", "title": "Predictively Oriented Gaussian Process Posteriors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03025", "title": "Verifiable, Articulable, and Tacit Components of Preference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02795", "title": "Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02626", "title": "Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02610", "title": "Seer: Maximum Likelihood Regression for Learning-Speed Curves", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02600", "title": "When History Misleads: Asymmetric Margin Supervision for Instruction-Guided LLM Generative Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18883", "title": "Token Utility for On-Policy Distillation via Local Trust-Region Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02057", "title": "Optimizing Effective Training Time for Large-Scale Recommendation Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "effective-training-time", "detail_path": "reproductions/2610.02057-effective-training-time/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01894", "title": "A foundation for systematic analysis of transformers and RNNs for tractography", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01746", "title": "End-to-End Learning vs. Modular Architectures: Comparative Insights into Autonomous Driving Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01738", "title": "Participation-Sensitive Convergence and the Fragment First, Converge Later Pattern in Asynchronous Online Learning: A Topological Analysis Across 22 OULAD Courses", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01705", "title": "AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized Recommendation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "agent-web-rec", "detail_path": "reproductions/2610.01705-agent-web-rec/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01533", "title": "Neither Black nor White: Balancing Semantic and Collaborative Signals with Graph-Informed Semantic IDs (GrIS)", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "gris", "detail_path": "reproductions/2610.01533-gris/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01316", "title": "What Wins a Vote? Formatting, Length, and Lexical Diversity in the French Compar:IA LLM Arena", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01270", "title": "Not All Is Lost: Repairing Lossy User Preference States of Personalization Encoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "repair-state", "detail_path": "reproductions/2610.01270-repair-state/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00984", "title": "HADRec: A Hierarchy-Aware Drug Recommendation Framework by Fusing Molecular Knowledge and Electronic Health Record", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18881", "title": "Following the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18880", "title": "Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18879", "title": "Do Vision CIL Methods Transfer to Protein? A Diagnostic Benchmark of Frozen Protein Encoders", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18878", "title": "Inverse Reasoning Models for Efficient Post-Training and Verification from Answer-Only Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18877", "title": "Lotus: Learning to Understand Time-series by Learning to Forecast", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10560", "title": "Strategic Governance of AI Models in Earth Science", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00654", "title": "When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.36484", "title": "The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "ride-opd", "detail_path": "post-training/2609.36484-ride/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2609.35445", "title": "NeuronSifter: An Agent-in-Twin for Prioritizing Central Nervous System Interventions with World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.35338", "title": "NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.34474", "title": "Deep kernel hedging", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.33291", "title": "The Statistical Benefits of Multiple Responses for Learning from Demonstrations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.32429", "title": "PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.32384", "title": "TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.32363", "title": "DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.30819", "title": "Learning Provable Neural Network Observer for Uncertain Dynamical Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.28399", "title": "Memory Attention", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.28248", "title": "hyperbolix: Hyperbolic Deep Learning in JAX", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.27043", "title": "EduBehaviors: Assertion-based Schemas for Auditable Coding of Educational Dialogues", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.25833", "title": "ARAFA: An LLM-Generated Arabic Fact-Checking Dataset", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.18437", "title": "When RAG Doesn't Help: LLMs for Plausible Material Prediction of Vehicle Components", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.18381", "title": "Every Fixed Metric Has a Blind Spot: A Learned Atmospheric Critic for Scoring Forecast Realism", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.13050", "title": "A Unified and Constrained View of Regularization-Based Robust Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.10886", "title": "Relatively Smart II: Tractable or Semi-Supervised Instance-Optimal Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.08594", "title": "Structured Multi-Level-Set Inversion for 3-D Electromagnetic Inverse Scattering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.06154", "title": "Rethinking One-Shot Federated Graph Learning: Training-Free Statistical Estimation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.04861", "title": "When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.04047", "title": "The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand Recommendations", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.01449", "title": "Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.27394", "title": "RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.27296", "title": "LLMs Can Design Near-Optimal OR Algorithms", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.29584", "title": "A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.24065", "title": "Mechanistic Circuit Identification for Controllable Data Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.24049", "title": "Physics-Integrated Operator Learning via Gaussian Splatting Representations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.12027", "title": "Uncertainty-Aware Probabilistic Constrained Clustering from Entangled Pairwise Supervision", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.11669", "title": "Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "rubric-dropout", "detail_path": "post-training/2608.11669-rubric-dropout/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2608.14706", "title": "Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.10232", "title": "FACT: Failure-Aware Causal Training for World-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.05025", "title": "Comparing SGLD and a fixed-noise predictor-corrector adaptation in canonical joint energy-based models on CIFAR-10", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.04962", "title": "SPARK: Learning from Verification in Speculative GRPO Rollouts", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "specroll", "detail_path": "post-training/2608.04962-specroll/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2608.16925", "title": "Wrong Operator or Blind Design? A Post-Training Diagnostic for Physics-Informed Coefficient Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.03172", "title": "Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.29606", "title": "QASP: Query-Adaptive Robust Vector Search Policy", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.24041", "title": "The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.22299", "title": "Hopformer: Homogeneity-Pursuit Transformer for Time Series Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.15482", "title": "Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.13609", "title": "Gauge-Invariant, Parameter-Insensitive Regularization for Potential Recovery from Flow on Directed Graphs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.13319", "title": "Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.12645", "title": "AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.10669", "title": "tidyHEBO: Improving the Robustness of Heteroskedastic Evolutionary Bayesian Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.10203", "title": "Does Depth Survive Composition, and Can a Router Use It? Adaptive Compute in Latent World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.09015", "title": "Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.08234", "title": "RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.08093", "title": "CausalDS: Benchmarking Causal Reasoning in Data-Science Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.05381", "title": "What Does a Discrete Diffusion Model Learn? One Reverse Process in Three Coordinates", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.05175", "title": "Platonic Projection Structures: Operator-Induced Observability in Representation Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.02417", "title": "LIME: Learning Intent-aware Camera Motion from Egocentric Video", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.29403", "title": "Self-Organized Conformal Prediction: Reducing Regional Coverage Gaps with Unsupervised Group Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.29240", "title": "Blackknife: Query-Free Black-Box Rewiring Attacks on Heterogeneous Graph Neural Networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.26277", "title": "From Clicks to Intent: Cross-Platform Session Embeddings with LLM-Distilled Taxonomy for Financial Services Recommendations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.24967", "title": "Geological text descriptions in ill-posed inverse problems: insights from learned hydraulic-conductivity inversion", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.22278", "title": "X-Safe: Embodiment-Agnostic Safeguarding for Robot Arm Manipulation Policies via Action Masking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.21139", "title": "PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.16285", "title": "HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.15251", "title": "Driving, Fast or Slow? Neuro-Symbolic Guidance for Motion Prediction in Multi-Modal Ground Mobility", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.11350", "title": "When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.09653", "title": "A Unifying Framework for Concept-Based Representational Similarity", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.09138", "title": "AgentWorld: A Data Factory for Training LLM Agents from Multi-Turn Interactions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.08682", "title": "Activation Steering Induces Emergent Misalignment: Steering Vector Construction and Comprehensive Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.07036", "title": "STREAM: Stochastic Riemannian Flow Matching with Anisotropic Decoder for Digital Histopathology Image Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.07690", "title": "HARP: Efficient Data Selection for Finetuning Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.31163", "title": "Memory by Design: Bayesian Layers for Sequence Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.31111", "title": "Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.28165", "title": "Unification and Optimization of Robust Supervised Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.23258", "title": "A Simple Plug-in for Improving Eviction-Based KV Cache Compression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.19660", "title": "OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.19330", "title": "MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.19324", "title": "BrainDyn: A Sheaf Neural ODE for Forecasting and Generating Brain Dynamics", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.19156", "title": "How Far Are We From True Auto-Research?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.01244", "title": "Retrieval-Augmented Generation to Support Railways Engineering Tasks: A Case Study", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.18106", "title": "Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, and MoE Routers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.15959", "title": "When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.15470", "title": "Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.22845", "title": "A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.15250", "title": "GQLA: Group-Query Latent Attention for Hardware-Adaptive Decoding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.12484", "title": "Learning, Fast and Slow: Towards LLMs That Adapt Continually", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.12461", "title": "A proximal gradient algorithm for composite log-concave sampling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.12000", "title": "Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.09742", "title": "TIDES: Implicit Time-Awareness in Selective State Space Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.09424", "title": "TabFORGE: A Tabular Foundation Model for Generative Modelling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.08733", "title": "Generative Actor-Critic with Soft Bridge Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.10980", "title": "LEAP: Unlocking dLLM Parallelism via Lookahead Early-Convergence Token Detection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.07191", "title": "Attention Transfer Is Not Universally Effective for Vision Transformers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.07057", "title": "From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.06727", "title": "Medical Imaging Classification with Cold-Atom Reservoir Computing using Auto-Encoders and Surrogate-Driven Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.26370", "title": "Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.25572", "title": "Dictionary learning for Kernel EDMD", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.21334", "title": "Ideological Bias in LLMs' Economic Causal Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.18508", "title": "Document-as-Image Representations Fall Short for Scientific Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.17998", "title": "Causally-Constrained Probabilistic Forecasting for Time-Series Anomaly Detection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.17883", "title": "Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.12234", "title": "UniRec: Bridging the Expressive Gap between Generative and Discriminative Recommendation via Chain-of-Attribute", "review_decision": "reviewed_deferred", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "unirec-coa", "detail_path": "reproductions/2604.12234-unirec-coa/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2604.08905", "title": "StaRPO: Stability-Augmented Reinforcement Policy Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.06163", "title": "Relevance Supervision Can Teach Neural Retrievers to Prefer LLM-Generated Text", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.28916", "title": "Structural Pass Analysis in Football: Learning Pass Archetypes and Tactical Impact from Spatio-Temporal Tracking Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.26030", "title": "Constitutive parameterized deep energy method for solid mechanics problems with random material parameters", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.23305", "title": "Sharp Statistical Thresholds for Attributed Gaussian Graph Matching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.18965", "title": "Maximum-Entropy Exploration with Future State-Action Visitation Measures", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.14426", "title": "GenState-AI: State-Aware Dataset for Text-to-Video Retrieval on AI-Generated Videos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.13535", "title": "Edgewise Envelopes Between Balanced Forman and Ollivier-Ricci Curvature", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.09200", "title": "The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.06977", "title": "NePPO: Near-Potential Policy Optimization for General-Sum Multi-Agent Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.04949", "title": "TimeWarp: Evaluating Web Agents by Revisiting the Past", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.00720", "title": "MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.00191", "title": "Task-Driven Subspace Decomposition for Knowledge Sharing and Isolation in LoRA-based Continual Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.11965", "title": "Parameter-Efficient Temporal Domain Generalization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.10326", "title": "Flow Matching with Uncertainty Quantification and Guidance", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.09009", "title": "ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.08519", "title": "Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.08318", "title": "Is Flow Matching Just Trajectory Replay for Sequential Data?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.08302", "title": "On the Dynamics of Delayed Generalization in Linear Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.07599", "title": "Rational Transductors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.00717", "title": "Deep Time-series Forecasting Needs Kernelized Moment Balancing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.21649", "title": "SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.16834", "title": "Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.20875", "title": "Beyond Sustainable Development Goal (SDG) Accelerators: Directed Evidence for Adaptive Sustainability Portfolios", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.12355", "title": "Tree-Structured Synergy of Large Language Models and Bayesian Optimization for Efficient CASH", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.07871", "title": "Imaging-anchored Multiomics in Cardiovascular Disease: Integrating Cardiac Imaging, Bulk, Single-cell, and Spatial Transcriptomics", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.22814", "title": "Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.12066", "title": "The Instability of Safety: How Random Seeds and Temperature Expose Inconsistent LLM Refusal Behavior", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.10309", "title": "Tracking large chemical reaction networks and rare events by neural networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.07384", "title": "On the Impact of Graph Neural Networks in Recommender Systems: A Topological Perspective", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.10831", "title": "A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.08860", "title": "When is a System Discoverable from Data? Discovery Requires Chaos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.04473", "title": "Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.02657", "title": "A Byzantine-Robust Federated Learning with Nesterov Momentum", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.22833", "title": "Toward Agents That Reason About Their Computation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.08464", "title": "Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2509.23209", "title": "Context Value Informed In-Context Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2509.20645", "title": "Anticipatory Evaluation of Language Models: Predicting LLM Benchmark Scores from Descriptions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2508.16939", "title": "Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2507.19465", "title": "Linearly Convergent Algorithms for Nonsmooth Problems with Unknown Smooth Regions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2507.14843", "title": "The Invisible Leash: Why RLVR May or May Not Escape Its Origin", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2507.13638", "title": "State Space Models Naturally Produce Time Cell and Oscillatory Behaviors and Scale to Abstract Cognitive Functions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2505.13771", "title": "Score-Based Training for Energy-Based TTS Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2506.06297", "title": "Rule-based and reinforcement-learning policies for resource allocation in a pediatric echo lab: a simulation study", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2505.12010", "title": "Incentivize Contribution and Learn Parameters Too: Federated Learning with Strategic Data Owners", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2504.07170", "title": "Trustworthy AI Must Account for Interactions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2502.11680", "title": "Spectral structure learning for clinical time series", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2501.05559", "title": "Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2412.08016", "title": "GLL: A Differentiable Graph Learning Layer for Neural Networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2410.19371", "title": "Noise-Aware Differentially Private Variational Inference", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2404.01867", "title": "Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2402.05203", "title": "Bellman Conformal Inference: Calibrating Prediction Intervals For Time Series", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2311.04902", "title": "Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2310.12765", "title": "Energy-Based Models For Speech Synthesis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2112.09646", "title": "Generation of data on discontinuous manifolds via continuous stochastic non-invertible networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10556", "title": "LIFT: A Lifecycle-aware Interaction Factorization Transformer for Unified Retrieval and Ranking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13989", "title": "PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00253", "title": "System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00251", "title": "The Null Is the Hard Part: Exact Tests for Memorization in Generative Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00054", "title": "The First Token Is Not the Verdict: Hidden Costs of Reading LLM Judges Without Generating", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20610", "title": "Can Learning to Answer Spatial Questions Improve Novel-View Generation?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20609", "title": "SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20604", "title": "VITAL: From Visual Motion to Precise Action", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20596", "title": "CoWear: Towards Collaborative Wearable Inertial Localization with Multiple Smart Devices", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20592", "title": "GeoThinker-$F$: Endogenous Predictive World Representations for Fast Spatial Intelligence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20579", "title": "PingpongDuo: Agile Humanoid Table Tennis Doubles with Safe Team Coordination", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20570", "title": "Manacá-1B-Instruct-2: Reproducible Safety Alignment for a Native Brazilian-Portuguese LLM. Negative DPO Results, a Controlled Composition Scan, and a Silent Failure Mode of the LLM Judge", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20563", "title": "Scaling Discovery Requires Forgetting", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20560", "title": "PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20552", "title": "KinoGen: Customizable Humanoid Loco-Manipulation References via Kinematically Grounded Video Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20548", "title": "PerSo: Investigating Facets of LLMs' Social Intelligence in Real-World Persuasion Scenarios", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20531", "title": "EarlyCommit: Calibrated Word-by-Word Commitment for Robots Acting Before You Finish Speaking", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20524", "title": "Physical Time as a Missing Dimension of Robot Policy Memory Dynamics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20504", "title": "Graph-Reweighted Behavior Cloning with Human Interventions for Precise Robotic Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20490", "title": "Towards Certifiable State Estimation under Observability Degeneracy", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20476", "title": "Tiered-Resolution Volumetric Mapping for Real-Time Simultaneous Planning and Mapping on Natural Outdoor Environments", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20474", "title": "AdaRSI: On-Demand Recursive Self-Improvement for Embodied Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20472", "title": "ChronoCulture: Evaluating Cultural Awareness Across Time in Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20461", "title": "Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20460", "title": "DD-GBP: Anytime Multi-Arm Planning and Continuous Execution via Distributed Dynamic Gaussian Belief Propagation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20457", "title": "Same Claim, Different Interpretations: How LLM Agents Resolve Ambiguity in Scientific Claims", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20442", "title": "Towards Agentic Robots: Model, Data, Environment, and Harness", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20429", "title": "When Do Discrete Actions Make Good Continuous Controllers?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20419", "title": "Analyzing performance of Retrieval Augmented Generation models for Question Answering Tasks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20417", "title": "From Unreliable to Usable: Decomposing Failure Modes and Confidence Signals in LLM Entity Extraction - Evidence from Cyber Threat Intelligence", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20390", "title": "STP-GUI: Spatially-Aware Token Pruning for Efficient Web-GUI Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20370", "title": "From Triage to Impact: A Multi-Hop Reasoning Benchmark for Explainable Persian Hate Speech", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20365", "title": "Lexical Persistence Without Semantic Entrenchment in AI Agent Communities", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20352", "title": "ReferFlow: Beyond Final-Target Localization for Complex Referring Expressions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20351", "title": "Human Demonstrations as Post-Training Data for Any Robot Body: Retargeting the Object, Not the Hand", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20336", "title": "AutoRSR: Automated Real-to-Sim-to-Real Data Generation for Scalable Robot Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20335", "title": "Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20333", "title": "VIGOR-MPC: Vision-Guided Objective Regulation MPC", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20320", "title": "TacClaw-Infinity: A Large-Scale Vision-Tactile-Language-Action Dataset for Dexterous Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20319", "title": "Beyond Static Cues: Unified Dynamic Detection of MLLM Backdoors via Dual-Flow Trajectory Analysis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20292", "title": "Taking the PULSE of Medical Reasoning: Step-Level Retrieval Timing for Knowledge-Grounded Inference", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20280", "title": "Learning-Based Adaptive MPC for Magnetorquer-Only Satellite Attitude Control", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20272", "title": "CSWBench: Evaluating Context-Sensitive Code-Switching in Creative Writing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20263", "title": "Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20255", "title": "Safe Reinforcement Learning with Receding-Horizon Safety Critic and Differentiable Action Shields", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20244", "title": "FPTAS for Polygonal Multi-Robot Motion Planning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20241", "title": "Learning Navigation from Multimodal Demonstrations with Geometric Candidate Modes", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20226", "title": "Smart Fusion for Adaptive Visual-IMU Weighting in cuVSLAM Sparse Bundle Adjustment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20223", "title": "ObjDream: Guiding Vision-Language-Action Models with Object-Level Understanding and Future State Prediction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20221", "title": "Scaling Multilingual Safety and Reasoning Evaluation through Reasoning-Guided Translation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20195", "title": "What Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20186", "title": "When Occupation-derived Skills Don't Help: On the Limits of Skill-Augmented Career Path Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20157", "title": "Atomic-WAM: Execution-Grounded Atomic-Motion Reasoning for World Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20155", "title": "LLM-Based Policy Compliance Verification of Loan Applications", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20150", "title": "Enabling Tidying Tasks in Robotic Vacuum Cleaners via a Geometry-Induced Self-Locking Deployable Linkage", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20134", "title": "Tactile-Guided Robot Learning: From Representation Learning to Foundation Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20121", "title": "HM3D-M3: A Benchmark for Multi-Agent, Multi-Modal, Multi-Object Goal Navigation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20107", "title": "Why Generate a Click? Plug-in Decision Heads for Web Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20086", "title": "AFCS: Atomic-Fact-Conditioned Synthesis for Factual Knowledge Pretraining", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20085", "title": "Designing Textual Interfaces To Enhance Llm Reasoning On Audio-Visual Question Answering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20083", "title": "VisualWorldBench: A Fine-Grained Multi-Task Benchmark for Evaluating Visual World Knowledge in MLLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20067", "title": "Which Knowledge Should LLMs Trust? Uncovering a Generalizable Steering Direction Across Knowledge Conflicts", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20064", "title": "FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20055", "title": "GeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20027", "title": "LintEval: Benchmarking LLMs on Linter-Guided File Refactoring", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20019", "title": "MorphAct: Robot Policies Morphing with the Worlds They Act In", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19996", "title": "Gray-Box Hallucination Detection in LLMs with Token Identities", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19993", "title": "Why 3D Reconstruction Breaks Down on Under-Ice AUV Video, and How to Predict It", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19992", "title": "SoK: Grading Open-Text Legal Answers, from Law School Exams to Trustworthy Rubric Judges", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19957", "title": "Complementary Future Token Pruning for World Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19928", "title": "MemDuet: Learning Dual-Process Memory for Long-Context Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19915", "title": "Not All Criteria Matter: Importance-Aware Criteria Weighting for Rubric-Based LLM Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19913", "title": "MUCO: A Mani-Unit-Structured Manipulation Framework for Compositional Long-Horizon Robot Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19906", "title": "Beyond Benchmark Accuracy: A Diagnostic Test for LLM Chemical Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19896", "title": "Active Perception of Upper-Limb Functional Mobility through Human-Robot Handovers", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19890", "title": "Frustratingly Easy Majority Voting Using Length Conditioning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19869", "title": "SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19839", "title": "FOMI: A Force-Feedback Manipulation Interface for Teaching Contact-Rich Manipulation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19830", "title": "DarKnight: Retrieval-Guided Agentic Framework for Breaking Dark Web CAPTCHA Gates", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19825", "title": "What Matters for World Modeling in Vision-Language-Action Models?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19823", "title": "PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19815", "title": "Learning from Demonstrations meets Symbolic Control - A Supervisory Control Architecture for Formal Certification of Learned Motion", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19801", "title": "Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19799", "title": "Evolve Together, Fall into Place: How Social Scaffolding Shapes Self-Evolving Multi-Agent Systems", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19798", "title": "Design and Characterization of a Unified Continuum Robot Actuation Platform", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19767", "title": "Likelihood Is Not Authorship: Can We Reliably Measure Human Contribution in AI-Assisted Writing?", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19765", "title": "Refine Actions If Needed: Adaptive Action Chunk Refinement for Robot Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19762", "title": "PRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19759", "title": "Mixed-Reality Feedback Control: Towards Blending of Control and Digital Twinning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19758", "title": "Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19753", "title": "Coordi-pi: Coordination-Aware Dual-Hand Action Representation for Bimanual Dexterous Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19746", "title": "One-shot Human Video-Guided Adaptation for Vision-Language-Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19742", "title": "HyperLoop: Hyperspectral-Assisted Loop Closure Detection in 3D-SLAM for Planetary Exploration", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19741", "title": "Does the Linguistic Register of Thinking Matter? Wenyan as a Compact Reasoning Register for Chinese LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19728", "title": "Mitigating Video Hallucinations via Attention-Guided Representation Perturbation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19723", "title": "Recognizing Dialogue Ambiguity via Candidate Set Visual Grounding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19714", "title": "Uncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19705", "title": "RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19704", "title": "BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19696", "title": "Share the Symbol, Not the Vector: Training-Free Fact Communication Across Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19677", "title": "ACRO: Actor-Critic Rollout Orchestration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19659", "title": "Measuring and Reducing Unusable Replies of LLM Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19656", "title": "Accelerating VLA Inference with Perturbation Informed Execution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19651", "title": "SPECTRA-VLA: Base-Fine Hyperspectral Token Transfer at Frozen Vision-Language-Action Interfaces", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19638", "title": "J-tau: A Fully Localized Japanese Benchmark for Tool-Agent-User Interaction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19635", "title": "Eye, Robot: Learning Expressive Gaze Dynamics via a VLM-Guided Transformer-VAE", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19627", "title": "E2DRL: End-to-End Differentiable Reinforcement Learning for 3D Obstacle Avoidance in Quadruped Robots", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19618", "title": "F2A-ObjectNav: An Adaptive Agentic Architecture for Object-Goal Navigation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19617", "title": "Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19615", "title": "PolyMorph: Learning Locomotion Policy for Cross-Embodiment Adaptation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19613", "title": "Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19611", "title": "What Breaks in Multi-Image Schema Application? Factorial Oracle Interventions Reveal an Instance-Information Bottleneck", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19604", "title": "ForceBench: Benchmarking Force Integration for Robotic Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19601", "title": "PA1-OPD: One-Step Prefix-Augmented On-Policy Distillation for Language Model Pretraining", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19600", "title": "Cracking Mobile Manipulation: From Failure Diagnosis to Agentic Robot System", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19594", "title": "RoboSpan: Learning Modular Coordination Policies for High-DoF Whole-Body Mobile Manipulation with Teleoperation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19587", "title": "Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19579", "title": "Back on Track: Deployment-time Policy Improvement via World Model Planning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19571", "title": "LED-BENCH: A Benchmark for Large-format Engineering Drawing Understanding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19560", "title": "$τ$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19551", "title": "TextVerifier: Seeing Beyond Recognition to Verify Chinese Text Rendering", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19549", "title": "GraphRAG-LTM: A Layered Threat Modeling Framework for Attacks on Graph Retrieval-Augmented Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19541", "title": "GS-PRM: Gaussian Visual Roadmap for Image-Goal Navigation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19527", "title": "Dual-arm Cooperation for Tabletop Wiping with Temporal Object Removal", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19523", "title": "Dungeon and Visibility World Generator", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19518", "title": "HiFun: a Hierarchical Framework for Efficient Functional Dexterous Manipulation Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19517", "title": "VLRLA: Deployment-Time Adaptation of Vision-Language-Action Models through In-Context Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19510", "title": "One Block Ahead: Promoting Sampler State in Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19497", "title": "Structure-Preserving Document-Level Data Augmentation via Discourse Parsing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19495", "title": "Robota-Embed: Unified VLA Embeddings for Robot In-Context Learning and Evolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19492", "title": "Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19481", "title": "IMU-Bench: Benchmarking Wrist IMU Representations Across Kinematic, Semantic and Clinical Tasks", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19479", "title": "Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19475", "title": "ActICL: Post-Training for Agentic Multimodal In-Context Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19465", "title": "Spacecraft Pose Tracking via Kinematic Prediction and Selective Event Correction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19443", "title": "More Than Seeing: Vision as Scalable Anchors in Native Multimodal Pre-Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19438", "title": "Paraphrase Consensus Is Not Self-Consistency: Instruction Reliance and Robustness in VLA Policies", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19431", "title": "$S^3$-Nav: Structured Spatial-Semantic Decision Making for Language-Guided Robot Navigation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19427", "title": "How Do LLMs Understand Legal Philosophy? Diagnosing Legal-Philosophical Reasoning in LLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19424", "title": "VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19420", "title": "From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19419", "title": "WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19413", "title": "A VR Training System for Robot-Assisted Vascular Intervention with Dual-Mode Control and Model-Based Interaction Response", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19408", "title": "ForkGRPO: Efficient Exploration and Fine-Grained Credit Assignment for Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19407", "title": "Vision-Language Models Integrate Conflicting Evidence Like Biased Bayesian Observers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19403", "title": "Topology-Preserving Multi-Usage Pipe Centerline Refinement under Permanent Tubular Occupancy", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19395", "title": "A Master-to-Simulation Interface with Demonstration-Trajectory Guidance for Vascular Intervention", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19393", "title": "Beyond Kinematic Tracking: Preserving Expressive Characteristics in Humanoid Whole-Body Control", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19380", "title": "Learning What to Keep: Transfer-Aware Personal Skill Learning from User Feedback", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19373", "title": "Evaluating Compressed Memory: Dependence, Utility, and Content Benefit", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19367", "title": "Beyond Corrected Actions: Training LLM Agents on Textual Critiques", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19366", "title": "Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19361", "title": "VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19341", "title": "MMKG-R1: Constructing Multimodal Knowledge Graphs via Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19336", "title": "Probabilistic Physics Digital Twin for Human-Robot Interaction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19331", "title": "LLM-jp-4 Technical Report", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19330", "title": "NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19316", "title": "Truthful and Expected-Payment-Optimal Model Routing in Graph-Based Agentic Workflows", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19314", "title": "PersEvalBench: Can LLM Evaluators Judge Contextually Appropriate Use of Persona Information?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19295", "title": "Learning Keypoint Constraints from Visual Demonstrations for Safe Motion Planning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19294", "title": "Qwenfant: Train Big Character-level BabyLMs on Concise Parallel Text", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19291", "title": "Can LLM Agents Efficiently Identify Appliance Faults? Insights From Diagnosing a Simulated Appliance", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19267", "title": "MemeTrace: A Multimodal LLM-Based Agent for Safety-Aware Meme Provenance Analysis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19266", "title": "LAMP: 3D Source-Aware Lighting Estimation at Multiple Points", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19262", "title": "MIND: Instruction-Conditioned Incremental Grounding for Robots", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19250", "title": "Full-Order Safety for Nonlinear Reduced-Order MPC", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19248", "title": "PACER: Process-Aware VLA Policy Learning from Human Corrections for Robotic Disassembly", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19247", "title": "Copy-Paste Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19224", "title": "End-to-End Vision-Language-Action Policies for Autonomous Lunar Rover Docking", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19210", "title": "Titan-Llama: Retrofitting Pre-trained LLMs with External Neural Memory Modules", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19206", "title": "DUALVIEW: Leveraging Broad and Output-Specific Evidence for LLM-based Multi-Output Text Regression", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19202", "title": "Weighted Ensemble Sampling for Rare-Event Estimation in Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19201", "title": "Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19190", "title": "NEPSEE: A Double-Annotated Benchmark for Nepali Sentiment Analysis", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19184", "title": "HERO: Harnessing Evidence for Test-time Refinement and Prompt Optimization in Program Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19183", "title": "A Mode-Unified, Continuous, and Biomimetic Control Strategy of a Robotic Lower Limb Prosthesis", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19166", "title": "Fantastic Metrics and How to Find Them: Meta-Evaluating Metrics for Multi-lingual Style-Personalized Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19165", "title": "ListQA: A Benchmark for Evaluating List-Formatted Factual Knowledge Retrieval in Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19157", "title": "DivAlgo: A systematic evaluation of algorithmic diversity for code generation models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19155", "title": "FACT: A Multimodal Force-Action-Track Foundation Model for Human-to-Robot Dexterity", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19143", "title": "Post-Training, Finetuning, and Steering:A Field Guide for Curating Training Data", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19141", "title": "Collective Learning for Unified Robotic Manipulation via Predictive Dynamics Adaptation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19131", "title": "Plant Memory: Technical Language Processing and a Verified Maintenance Ontology for Agent-Accessible Failure Knowledge from SAP PM Work Orders", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19122", "title": "Learning in Orbit: Onboard Training and Closed-Loop Attitude Control with a Thermal Segmentation Model on a Spacecraft", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19118", "title": "DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19108", "title": "Towards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19102", "title": "The Gap Is in the Geometry: A Convergent Meta-Analysis of Multi-Facet Aerial and Remote Sensing Video Understanding", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19100", "title": "GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19097", "title": "Benchmarking 3D Reconstruction for Under-Ice Robotic Perception in Arctic Environments", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19091", "title": "DiffGIPC: Differentiable Mixed-Coordinate Contact Dynamics on GPU", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19089", "title": "DexMimic: A Generalist Dexterous Hand-Object Tracking Policy via Value-Guided Reset Allocation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19082", "title": "Receding-Horizon Next-Best-View Planning for Highly Occluded Target Perception", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19067", "title": "Tread: A Visuo-Inertial Framework for Terrain and Locomotion Context-Aware Gait-Phase and Speed Estimation in Wearable Robotics", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19052", "title": "Why Do VLMs Fail at Remote Physiological Measurement? Rethinking with Physiological Grounding and Numerical Alignment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19048", "title": "Pre-Trained Language Models as Zero-Shot Tools for Social Science Research", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19044", "title": "RingNav: Task-Shaped Circular Memory for Visual Heading", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19026", "title": "Joint Subspace Sparse Attention for Efficient Long-Context Decoding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19021", "title": "Can LLMs Access their World Knowledge for Event Prediction?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19003", "title": "Evaluating Large Language Models for Multilingual Abstractive Summarization: A Comprehensive Study of English and Bengali", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18991", "title": "Contact-UAN: Unsupervised Actuator Networks as a Residual World Model for Humanoid Control", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18874", "title": "ChunkAct: Action Chunking for Agentic Robotics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18873", "title": "LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment Rollouts", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18869", "title": "What Matters in Quality-Aware VLA Pretraining: A Benchmark and Empirical Study", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18868", "title": "Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18867", "title": "EmbodiedEvo: Self-Evolving Coding Agent For Physical Intelligence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18862", "title": "DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18861", "title": "Hybrid Reasoning Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18858", "title": "Visual Tokens on Demand: Visual Budgeting for Scalable and Efficient Multi-Image Reasoning in Multimodal LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18855", "title": "Interaction Latents as Actions for Contact-Rich Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18852", "title": "ForceWAM: Decoupling Future and Response Learning from Demo and Play Data for Contact-Rich Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18851", "title": "MFG: Multi-turn Feedback Guided Molecular Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18845", "title": "The Last Remote Sensing Model Built by Humans? Casting Any Earth Observation Task as Recursive Self-Improvement", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18844", "title": "RepProbe: Can Video Language Models Count Repeated Actions? A Diagnostic Benchmark", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18836", "title": "Plan-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18834", "title": "Game2Real-Bench: Do Toy Games Reveal and Transfer to Real-World Visual Reasoning?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18829", "title": "OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18820", "title": "Read the Room Before Your Model Generates", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18818", "title": "Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18809", "title": "Depth Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18807", "title": "SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18950", "title": "$λ_0$: Scaling Open-World Egocentric Human Data for Humanoid Loco-Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18792", "title": "SEAR: Self-Evolving Agentic Robotics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18786", "title": "Where Do LLM Ensemble Gains Come From? Decomposing Candidate Value, Diversity, and Aggregation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18780", "title": "BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18774", "title": "GreenWAM: A World Foundation Model for Robotics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18762", "title": "Looking Complete Is Not Being Grounded: Evaluating LLM Sitreps Against Human-Authored Situation Reports", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18729", "title": "Segment Where You Look: Attention as the Interface Between Language Models and Segmenters", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18726", "title": "Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18725", "title": "Learning Source Structure: Bayesian Prediction with Transformers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18724", "title": "AIRRI: Towards a Human-Readable, Machine-Resistant Reading Interface", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18697", "title": "UniW(A)M: A Unified Mixture-of-Experts Framework for World and World-Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18694", "title": "GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18690", "title": "Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18683", "title": "ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18649", "title": "Tiny Recursive Message Passing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18642", "title": "MultiAlloc: Budget-Aware Precision Allocation for KV Cache Quantization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18638", "title": "To Align or Not To Align: Check Your COMPASS Before You Train", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18624", "title": "MajorTOM:Elliot Pretrain, A Multi-Sensor, Multi-Temporal Pretraining Dataset for Earth Observation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18615", "title": "VideoJev: System One Model for Video Understanding and Interaction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18614", "title": "Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18609", "title": "DPOison-VL: Clean Preference Poisoning in Vision-Language Direct Preference Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18606", "title": "Beyond Answer Voting: Fine-Grained Correction of LLM Reasoning through Graph Alignment across Sampled Traces", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18605", "title": "From Hindsight to Foresight: Dissecting Clinical Evidence Acquisition in Large Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18604", "title": "LLM2R: From Large Language Models to 3D Reassemblers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18598", "title": "Rethinking Projector Training in Multimodal LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18588", "title": "Decomposing and Predicting Annotation Disagreement in Harmful Content Across Languages", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18572", "title": "LLM Agents for Automated Post-Training via Structured Recipe Optimization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18569", "title": "CREATE: Creativity Evaluation of VLMs using the Visual Remote Associates Test", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18568", "title": "WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18535", "title": "Meta-Video: Efficient Standardized Evaluation for Video Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18529", "title": "How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18520", "title": "The Geometry of Language Model Logits: Generic Structure and Learned Departures", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18516", "title": "Two For The Price Of One: Curvature-Aware Pruning Preserves Influence Functions Too", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18508", "title": "Towards Safe Autonomy for Computer Use", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18504", "title": "How Low Can You Go: Fine-Tuning LLMs with Bayesian Optimization (LlMBO)", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18499", "title": "EgoOmniWorld: Unifying Egocentric Understanding via Ego-Action-World Interactions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18497", "title": "Judges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18471", "title": "Graph Metanetworks for Transformer Based Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18457", "title": "Kairos: Transactional Security Enforcement at the System Boundary for LLM Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18455", "title": "EmoGenie: Benchmarking and Evaluating Expressed and Evoked Emotion in T2I Generation with MLLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18451", "title": "FastEEP: Fast Intra-Instance Elastic Scaling for Expert-Parallel MoE Serving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18447", "title": "Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18442", "title": "Copying Is Not Grounding: Training Faithful Long-Form RAG with Authored-Sentence Credit", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18420", "title": "Agaram 2.5B: The First Tamil-First Language Model Trained from Scratch with Tool Calling. A Playbook for Under-Represented Languages", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18415", "title": "Do Factuality Methods Make LLMs More Factual? Reproducibility and Fair Comparison", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18412", "title": "Not All Drift Is a Mechanism: Tracing Prompt Adaptation in LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18407", "title": "Multi-Stream Residual Computation in Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18399", "title": "Bifocal: Training-Free Mixed Granularity Visual Token Pruning for Multimodal LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18388", "title": "ReDiS: Reasoning-Diagnosis Self-Evolution for Multimodal Reasoning in Remote Sensing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18369", "title": "Hallucination-aware Faithful Reasoning in Remote Sensing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18359", "title": "Pin It on Anyone: Certified Targeted Displacement of Multi-Bit LLM Watermarks Without the Key", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18343", "title": "Lightweight but Linguistically Fair? Quantisation Robustness across Bavarian, German, and English", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18326", "title": "Jev-Guard: Fast Routing and Auditing Agent Actions over Editable Policy Trees", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18323", "title": "Omni-RS: Unifying Multi-Task Understanding and Generation in Remote Sensing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18299", "title": "LegalRewardBench: Benchmarking Reward Models for Legal Preference Evaluation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18295", "title": "Robust Logical Anomaly Detection under Capture Shifts via Synthetic Anomalies", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18269", "title": "PAINT: A Framework for Multilingual Pain Representation from Medical Licensing Exams to Real-World Clinical Texts", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18262", "title": "Encrypted Skills Can Become New Security Exploits If AI Agents Know How to Decipher", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18256", "title": "Teach Me After You Learn It: Lookahead Self-Distillation for RLVR", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18248", "title": "Are We Testing Too Much? A Survey of Benchmark Compression for Efficient Evaluation of Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18238", "title": "Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18216", "title": "TextualRL: Textual Reinforcement Learning for Context Management", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18210", "title": "Operator Surrogates", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18200", "title": "A Few More Tokens Ahead: Reinforcing Parallelism in Diffusion LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18176", "title": "Neuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18173", "title": "TRACESTEER: Trace Driven Activation Steering for Hallucination Mitigation in Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18161", "title": "Benchmarking Multimodal Large Language Models for Zero-Shot Human-Object Interaction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18159", "title": "Claim Framing as a Driver of LLM Sycophancy", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18157", "title": "Fan Out or Relay? Ownership-Aware Routing for LLM Agents Querying Siloed Tables", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18140", "title": "SparPR: Runtime KV-Cache Recovery for Resource-Constrained LLM Inference on Consumer Hardware", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18122", "title": "Cheap, Consistent, Calibrated, but Biased? Typed Decision Models as Judges", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18121", "title": "Narrative Lookahead in LLMs: Event-Level Decodability, Predictive Advantage, and Steering", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18108", "title": "A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18104", "title": "The Effect of Layer Ordering in Hybrid Architectures", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18085", "title": "Same Function, Different Trajectory: No Standard Optimizer Is Equivariant to Transformer Reparameterization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18051", "title": "inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18038", "title": "Data-Free Continual Learning for World Action Model with Rectified Generative Replay", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18025", "title": "SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18023", "title": "FRACTION: Fraud Explanation Generation via Agentic Graph Context Navigation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18019", "title": "Machine--human agreement in marking undergraduate assignments is specific to model, prompt and institution", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18001", "title": "Match the Canvas, Not Just the Answer: Predictability-Aware SFT for Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17991", "title": "PolUR: Polarization Aware Multimodal Degradation Perception for Underwater Image Restoration", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17989", "title": "Seeing Through the Forgery Is Not Enough: Regressive Sycophancy under Fabricated Evidence in Medical Vision-Language Models", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17977", "title": "ReEnvision: Future-Guided Selective Action Repair for Long-Horizon Manipulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17966", "title": "BELT : BEhavior-Aligned Low-Rank KV Cache Compression with Learned Top-k Rank Allocation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17959", "title": "Virtual Head Attention", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17953", "title": "Agent-Reflex: Teaching Language Agents to Act Reflectively", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17948", "title": "HaloBlock: Faster and Better Decoding for Diffusion Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17937", "title": "MERIT: Multimodal Evidence Reasoning over Image Tables", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17917", "title": "Batch-Paced: Fixed-Budget Batch Decoding in Discrete Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17908", "title": "Text-Only vs. Image-Aware VLM Judges for Manga Translation Evaluation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17903", "title": "DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17902", "title": "Visual Dependence Does Not Imply Answerability: A Systematic Analysis of Answerability Signals in Frozen InstructBLIP", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17901", "title": "FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17893", "title": "Training LLMs for Multi-Agent Collaboration with Verifiable Information Rewards", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17880", "title": "Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17868", "title": "Prefilling-dLLM v2: Learned Chunk Routing for Long-Context Diffusion Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17866", "title": "MicroCLIP: Connecting Text and Microscopy Images via Contrastive Language--Image Pretraining", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17853", "title": "DVTR-KD: Distilling Vision-Language Models via Intermediate Visual Token Reconstruction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17844", "title": "What Makes a Good Visual Representation for Spatial Understanding in MLLMs?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17831", "title": "Diff Diffusion: Predicting Edit Paths with Diffusion Models for Efficient Code Editing", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17824", "title": "Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17804", "title": "Learning from fracture: Teaching language models to design through physical experience", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17802", "title": "Beyond the End-Effector: Learning Whole-Arm Contact Manipulation from Human Demonstrations", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17794", "title": "GIFT-Eval-CTX: A Benchmark For Contextual Forecasting Model Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17792", "title": "MHVF: Training-Free GUI Grounding via Verification-Guided Multi-Hypothesis Search", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17791", "title": "When, Where, and Why: Hierarchical Causal Explainability for Video Face Understanding with MLLMs", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17786", "title": "Agentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17780", "title": "Full-duplex Spoken Language Modeling with Discrete Diffusion", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17777", "title": "Beyond Belief Nesting: Rethinking Higher-Order Theory of Mind in Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17751", "title": "Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17734", "title": "Explore with Memory, Learn without It: In-Context Exploration and Self-Distillation for LLM Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17733", "title": "CoCA: Criterion-Aware Credit Assignment for Rubric-Based Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17730", "title": "DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17727", "title": "SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17726", "title": "TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17706", "title": "From Token Correction to Claim Admission: Training-Free Hallucination Mitigation for Large Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17688", "title": "OccWAM: Occupancy World-Action Models with Joint Scene-to-Ego Flow Matching", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17686", "title": "Encoding Context into LLM Weights: What Makes It Context?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17673", "title": "RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17651", "title": "Code2Worlds-2: Physically Plausible Agent Harness for Embodied World Simulation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17640", "title": "MemAct: Streaming Spatial Understanding with Memory and Active Exploration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17639", "title": "FrameLite: Decision-Oriented Aesthetic Cropping with a Compact Vision-Language Model", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17638", "title": "Acting Through Registers", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17637", "title": "Mixed Precision Scaling Laws for Quantized Pretraining", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17636", "title": "The Tokens Strike Back: Safety-Aware Denoising with Directional Embedding-based Revision", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17633", "title": "Executable Prefix Values for Locating Agent Failures", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17630", "title": "From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17625", "title": "4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17597", "title": "TDR: Tagalog Diacritic Restoration Dataset", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17596", "title": "Tanawpamana: Benchmarking Vision-Language Models on Philippine Cultural Heritage Sites", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17590", "title": "Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17576", "title": "Dissociating Answerability from Extraction in LLM Question Answering over Radiology Reports", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17560", "title": "EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17544", "title": "Many Steps into One: Reasoning Contraction and the Limits of Safe Memory Reuse for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17531", "title": "Towards Green AI: Evaluating Energy Efficiency for Quantized LLM Inference", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17530", "title": "TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17528", "title": "ATTUNE: Agentic Throughput Tuning for LLM Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17526", "title": "Box-WAM: Box Trajectories as Compact State Representations for World Action Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17503", "title": "Foundation Models for Event Prediction Across Heterogeneous Event Logs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17456", "title": "Compositional RL: Evaluating and Training LLMs for Collaborative Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17440", "title": "Know-Thy-Not: Training-Free Targeted Negation in Dual-Encoder Vision-Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17426", "title": "Reinforcement Learning In Partially Verifiable Environments for Colon Cancer Treatment Planning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17402", "title": "Evaluating Temporal Reasoning in Large Language Models: Event Temporal Relation Extraction with Allen's Interval Algebra, Logical Consistency, and Relative Time in Narratives", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17399", "title": "Learning to Detect Shifts in Unstructured Data Streams via Monitoring-by-Betting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17397", "title": "JustOPD: On-Policy Distillation from Autoregressive to Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17387", "title": "Cross-Market Meta-Learning for Electricity Price Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17384", "title": "Measure Neural Mappings", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17379", "title": "EPOCH: Coverage-Aware Evolution with Experiential Preference Optimization for LLM-based Automated Heuristic Design", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17375", "title": "PIG: Parallel Inconsistency Guidance for Accelerating Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17363", "title": "UMCR: Universal Medical Concept Recognition through Guideline Integration and Agentic Linking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17358", "title": "claimcheck: Measuring and Improving Specification Faithfulness", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17355", "title": "WIRE: Weight Space Implicit Representation Encoding of Frozen Video LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17332", "title": "COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17321", "title": "GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17312", "title": "A Geometrical Approach to Constructing Neural Networks for Perfect Training-set Classification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17306", "title": "Calibrating LLM Explanations to Human Decisions with Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17269", "title": "Measuring Learned Equivariance: An Information Theoretic Approach", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17251", "title": "HybridDualPathNet: Cross-Fusion Attention of EfficientNetV2 and Swin Transformer for Brain MRI Classification of Alzheimer's and Parkinson's Disease", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17246", "title": "LLM-to-Flow Distillation: Teaching Natural Language Goals to Scientific Generators", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17243", "title": "From Conceptual EneMonIE to an Executable Backend: A Modular Architecture for Energy Information Extractionand Grounded Question Answering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17242", "title": "When Left Is Right? Camera-Motion Understanding beyond Screen", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17233", "title": "Beyond Sparse Captions: Aligning Slide-Level Text and Patch-Level Vision in Pathology", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17214", "title": "Density-Matrix Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17203", "title": "Online LLM Personalization from Pairwise Preferences Across Users", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17202", "title": "MLAfication: Efficiently Enabling High-Fidelity MLA for Modern LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17174", "title": "Generative Flow on Symbolic Abstractions for Embodiment Capability Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17164", "title": "Learning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17158", "title": "The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17143", "title": "OpenDGO: Benchmarking Multi-Agent Organizations Across Diverse Application Domains", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17141", "title": "MARS: Systematic Multi-Level Acceleration for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17125", "title": "ToolHACE: A Dataset for Detecting Hallucinations in Tool-Based LLM Responses", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17124", "title": "D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17118", "title": "When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17117", "title": "Gluing Local Contexts into Global Meaning: A Sheaf-Theoretic Decomposition of Transformer Representations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17096", "title": "Towards Universal Calibration for In-Context Classification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17079", "title": "Rethinking LLM-Guided Visual Question Answering: Does Deeper Knowledge Integration Really Help?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17077", "title": "UZHCL_for_the_win at Touche: Encoder Fine-Tuning, Synthetic Augmentation, and an Underpowered Encoder-LLM Comparison", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17065", "title": "TILE: Bridging LLMs and Table Foundation Models for Tabular Learning with Strings", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17062", "title": "Gradient Routing Localizes and Removes Unintended Behaviors in RL", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17042", "title": "AD4EDU: Benchmarking University Lecture Audio Description across Accessibility Standards, Metrics, and Learner Preferences", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17040", "title": "Beyond Model Bias: Cross-Entropy Based Rankings in Literary and Academic Texts Remain Stable across Small Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17039", "title": "MENTOR: Procedural Shielding of Tool-Using LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17018", "title": "LLM Evaluation is a Forecasting Problem", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16985", "title": "AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16977", "title": "The Value of Being Wrong: Self-Mined Visual In-Context Learning from Errors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16969", "title": "UniLAP: A Unified Latent Action Policy for Cross-Embodiment Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16966", "title": "Learning to Design SR Solvers: Harness Optimization for Symbolic Regression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16957", "title": "SarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16956", "title": "DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16945", "title": "UniMetric: Universal Metric Scale Recovery for Visual Geometry Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16933", "title": "Estimating Uncertainty of Omnimodal Large Language Models via External Omnimodal Embeddings", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16921", "title": "Time Window Optimization for Motor Imagery Classification via Temporal Structure Embedded Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16891", "title": "AI-Assisted Tumor-Growth Law Discovery from Sparse Data: Refitting and LLM-Based Ranking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16868", "title": "From Parallel to Sequential: Small-Batch Noise Restores Simplicity Bias of Muon", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16866", "title": "Efficient Resource-Shiftable RL Post-training with Generative Rewards", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16859", "title": "ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16857", "title": "Towards Cost-Efficient Video Dataset Construction with Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16839", "title": "Label Collapse in Diffusion Language Model In-Context Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16837", "title": "A Scaled-Up Empirical Study of Syntactic Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16828", "title": "The Bell Boundary of Shared Representations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16822", "title": "DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16817", "title": "Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16815", "title": "On the Calibration of Crowdsourcing Aggregators", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16812", "title": "DASS: A Solver-Adaptable Dynamic Auxiliary Search Strategy for Symbolic Regression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16793", "title": "ViewStruct: View-Grounded Articulation and Connectivity Inference", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16761", "title": "Separating Prompt Harmfulness from Interaction Safety via Partial Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16755", "title": "The Multilingual Artificial Hivemind: Do All LLMs Think Alike in Every Language?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16744", "title": "FoveaTree: Information-Density Trees for Query-Guided Visual Token Pruning in Video Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16722", "title": "Lost in Contrast: Instruction-Preserving Decoding for Reliable Visual Question Answering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16666", "title": "Revisiting Natural Language Prompts from Large Language Models for Open-Vocabulary Video Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16653", "title": "Counting with Attention and LayerNorm: Norm Scaling and Representation Geometry", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16641", "title": "What Limits Cross-Task Generalization in World Action Models?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16636", "title": "SuPER-Mamba: Surprisal Prioritization for Extended-Context Routing in Mamba", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16634", "title": "Language2Drive: Do Vision-Language-Action Models Really Follow the Instructions in Autonomous Driving?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16622", "title": "Answer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16592", "title": "Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16591", "title": "JtT: Rethinking Point Trajectory Diffusion for Diverse and Rigid Motion from an Image", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16579", "title": "LLM-HB: Language-Aware LLM-Guided Hotword Biasing for Code-Switching ASR", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16577", "title": "CineRecon: Benchmarking Frontier Models for Agentic Cinematic Reconstruction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16569", "title": "From a Large-Scale Teacher to Efficient Multimodal Students for Search Relevance Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16567", "title": "VLA-GAUGE: Systematically Evaluating Generalization and Robustness in Vision-Language-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16558", "title": "G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16533", "title": "Spectral-Driven Adaptive-Rank Optimizer for Large Language Model Reinforcement Learning with Verifiable Rewards", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16523", "title": "EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16517", "title": "Trust-Calibrated VLA Policy Post-Training with Evolving Imagination", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16516", "title": "Intent-Triggered Anchoring for Multi-Token Format Units in Parallel Decoding of Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16502", "title": "KARAMEL: Knowledge-Aware Ranking for Multimodal Entity Linking in the Arts via Heterogeneous Graphs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16490", "title": "Communication, Vocalisation, and Language", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16489", "title": "Growing and Transferring Pathways for LLM Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16482", "title": "MiMaAlign: Hierarchical Micro-Macro Alignment for Physically Plausible Video Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16465", "title": "Teaching Vision-Language Models to Decline: Support Completion Against Mirage", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16460", "title": "The interpreter as developer: An autoethnographic design study of building a computer-assisted interpreting tool through human-LLM co-creation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16455", "title": "GHOST: Geometry-Constrained Hybrid Diffusion for Open-Vocabulary 3D Scene Graph Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16451", "title": "StructZO: Structured Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16441", "title": "VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16391", "title": "RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16372", "title": "PersonaFactor: Preference Factors with Dynamic Selection for LLM Personalization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16371", "title": "Rule vs.Consequence: Dissociable Internal Representations of Moral Reasoning in LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16368", "title": "LoopQuant: Accurate and Efficient Post-Training Quantization for Looped Transformers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16364", "title": "From Sound to Sense: An Anatomy of Semantic Supervision for Speech-Driven Visual Grounding in Remote Sensing Imagery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16355", "title": "PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16352", "title": "A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16345", "title": "ChronoScribe: Semantic-Numerical Specialization for Instruction-Driven Time Series Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16343", "title": "Efficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16324", "title": "Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16318", "title": "Strong yet Controllable LLM Abstention without Learning to Abstain", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16305", "title": "ATTCK-R: Knowledge-Aware Long-Horizon Jailbreaking for Protected LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16299", "title": "Learning Temporal Evidence Selection for Video Anomaly Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16289", "title": "Fast Quantized Johnson$-$Lindenstrauss Transforms", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16288", "title": "REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16281", "title": "RelLedger: Relational Information Governance for LLM Agent Organizations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16264", "title": "Spectral Considerations on Unsupervised Time-domain EEG Representation Learning with Deep Networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16242", "title": "Same Goal, Different Words: Spatial Instruction Sensitivity in World-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16226", "title": "NetRL: Powering Network Decisions via NetGRPO-Driven Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16176", "title": "EgoAlign: Situated 3D Understanding without Situation Descriptions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16172", "title": "EventLens: Event-Structure Reinforcement Learning for Video Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16170", "title": "Geometric Parrots: Rule Absence vs. Rule Fragility in Spatial and Physical Reasoning for Vision-Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16165", "title": "Think Before You Speak: Enabling Training-Free Latent Communication Between Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16152", "title": "WildTrace: Evaluating Training Data Detection in Realistic Large-Scale LLM Post-Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16146", "title": "Unravel: Recovering an Interactive 3D Scene from a Single Image", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16144", "title": "Hashrope: A Persistent Data Structure for Mechanisms of LLM Context Management", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16143", "title": "All-St3R SLAM: Real-time RGB Dynamic SLAM with Pixel-wise Motion Masking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16141", "title": "Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16135", "title": "Omni-Modal LLMs Know More Than They Say", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16133", "title": "Query Your Way Out: Benchmarking Multi-Turn Knowledge Reasoning through Generalized Puzzle Solving", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16129", "title": "PID-Gated Continual Prompt Adaptation Under Noisy Feedback", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16120", "title": "Scaling Multi-Agent Intelligence with Substrate-Centric Coordination", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16118", "title": "Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16105", "title": "Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16071", "title": "Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16051", "title": "How the Classical Baseline Shapes Machine-Learning Speed Claims in Topology Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16043", "title": "Beyond the greenwash: do LLMs' ecologically sound decisions hold up under pressure?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16041", "title": "Autoregressive Decoding as a Martingale: Characterizing the Stochastic Dynamics of LLM Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16039", "title": "When Agents Talk, Secrets Travel: Topology-Driven Leakage and Recipient-Conditioned Sanitization in Multi-Agent LLM Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16009", "title": "Meaningful Moments: A Corpus of VLM-Derived Temporal Importance Labels for Video Action Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15963", "title": "Using Line Segment Tracking to enable ML-based Track Reconstruction in CMS", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15938", "title": "The Anatomy of a Blind Spot: What an LLM Judge Must Be Shown, and How Much", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15929", "title": "When Trackers Fail: VLM-Guided Verification and Recovery for Robust Video Object Segmentation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15924", "title": "Scalable Weak-to-Strong Verifier Hardening for Agent Environments", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15921", "title": "Fast and Accurate: Improving Personalized LLM Performance by Semantic Concentration Inspired Workload Split between RAG and Fine-Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15912", "title": "More Reasoning Is Not Always Better: Executing Clinical Guidelines with LLMs and Rules", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15899", "title": "Lightweight Scheduling Policies for Continuously Batched LLM Serving Across GPU Architectures", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15897", "title": "Review Rarely Beats the Stronger Model: Separating Verification from Capability Transfer in LLM Pipelines", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15894", "title": "Make Every Expansion Count: Learning to Search Efficiently in LLM Code Repair", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15891", "title": "Learning Multimodal Sensor Fusion with JEPA Representations for Breathing Activity and Pose Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15854", "title": "Sharper Frames, Worse Rooms: Viewpoint Coverage Dominates Image Quality in Feed-Forward 3D Reconstruction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15840", "title": "LLM Value Functions for Credit Assignment in Agentic RL", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15837", "title": "KhyontekAI at CheckThat! 2026: Multilingual Dense Retrieval and Cross-Encoder Reranking for Scientific Web Claims", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15836", "title": "Latent Taxonomies: How Property Induction Develops in Language Model Pre-training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15818", "title": "Benchmarking Deep Learning Models for Anomaly Detection in Real-World Cloud Telemetry", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15810", "title": "Adaptive Look, Flexible Thought: Learning How and How Long to Think in Multimodal Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15794", "title": "$Δ$ Flow Matching for Robot Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15788", "title": "Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15782", "title": "Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15781", "title": "Heterogeneous Structured Pruning Under Resource Constraints for Hardware-Efficient Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15772", "title": "RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "rsipo", "detail_path": "reproductions/2610.15772-rsipo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.15761", "title": "Robust Marathi Sentiment Analysis using Domain-Adaptive Pre-training and Data Augmentation Approaches", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15742", "title": "RSAJEV: Training-Free Abstaining Prototype Memory for Eliminating Silent Hallucination in JEV-Based Remote Sensing Classification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15732", "title": "NepPlural: A Human-Anchored Benchmark for Persona Annotation in Nepali Migration Discourse", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15728", "title": "Visually Legible but Adversarial: Watermark-Constrained Attacks on End-to-End VLMs for Document Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15722", "title": "PhySimCode: A Benchmark and Evaluation Method for Physics Video to Code Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15715", "title": "History Replays Itself: Unleashing Long-Context Capability in Linear Attention", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15712", "title": "TL;QR: Querying Temporal Discursive Patterns in Textual Corpora", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15709", "title": "Preserving Updates in Low-Bit Recurrent State Quantization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15707", "title": "Generalizable Model Editing Could Be More Than Direct Generalization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15692", "title": "Do LLM Tutors Actually Teach? A Process-Centered Synthesis of the Tutoring Loop", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15678", "title": "The Mathematical Collective Unconscious: Jungian Archetypes within the Latent Space", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15675", "title": "Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15667", "title": "Rate-Resolved Text Evaluation with Masked Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15666", "title": "A Persian Vision-Language-Action Dataset and Benchmark for Ambiguity- and Infeasibility-Aware Instruction-to-Plan Grounding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15660", "title": "Sparse All-Layer Connector for Domain Generalised Semantic Segmentation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15629", "title": "The Price of Precision: A Calibrated Cost Model for Mixed-Precision LLM Serving", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15625", "title": "1Step-WAM: Your World Action Model but Faster using 1-Step Action Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15585", "title": "StreamingWAM: Streaming World Action Modeling via Chunk-Wise Staircase Flow Matching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15578", "title": "Towards Robust Calibration Dataset for Domain-General Mixture of Experts Pruning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15574", "title": "The Fragility and Dynamics of LLM Pruning-Recovery Steps", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15565", "title": "Genesis: Visual Augmentation Primitives for Multimodal Chain-of-Thought Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15556", "title": "Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15555", "title": "ELECT: Settling Identity Before Rendering for Scalable Story Visualization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15542", "title": "Apertus 1.5: From Open Text Models to Open Multimodal Reasoners", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15527", "title": "A Step in the Right Place: Understanding and Optimizing Timestep Placement in Continuous Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15514", "title": "SARATHI: Decoupled Data-Free Probing and Adaptive Reconstruction for Structured LLM Pruning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15513", "title": "REPRO: Reflective Evolutionary Prompt Optimizer for Automated LLM Red-Teaming", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15496", "title": "Concept Representations in Vector Space: Quantifying Sharedness and Idiosyncrasy of Meaning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15488", "title": "AlphaPilot: Multi-Turn Tool-Using LLM Agents for Adaptive Alpha Mining with Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15467", "title": "Semantic Saliency from Multi-Modal Large Language Model Scene Understanding Maps", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15452", "title": "EmoTrace-Bench: Diagnosing Emotional Expression in Text-to-Video Generation through Controlled Cues and Intensity", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15449", "title": "Hidden in Plain Sight: Advancing Harmful Content Understanding via Perception-Aware Adversarial Self-Play", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15429", "title": "World Modeling through Spectral Alignment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15403", "title": "A Decade of PhotoMappers: A Longitudinal Study of Crowdsourced Disaster Photos Geolocalization with Vision-Language Models and Geospatial Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15398", "title": "GA-SVD: Generation-aware Singular Value Decomposition for LLM Compression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15390", "title": "From Acoustic Sensing to Physical Actions: A Comprehensive Survey of Security Risks in Edge-Deployed Audio LLM-Based Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15389", "title": "VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15384", "title": "E8 Lattice Key Quantization for Low-Bit KV-Cache Compression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15371", "title": "A Sovereign, Indic-First, Reasoning Model", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15365", "title": "TRACE: Temporal Risk Assessment and Concept Editing for Safer Language Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15337", "title": "CoLA: Multi-VLA Coordination via Learned Adapters", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15336", "title": "ZOIF: Zeroth-Order Influence Function Estimation for LLM Data Selection Using Only Forward Passes", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15328", "title": "Anchor-and-Harvest Curriculum: A Fully Unmasked Non-LLM Curriculum for Craftax", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15307", "title": "FENAS: A Few-Shot Meta-Ensembling Framework for Efficient Neural Architecture Search with Synergized Zero-Cost Proxies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15305", "title": "RM-WAM: Reliable Memory-Augmented World Action Models for Long-Horizon Robot Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15282", "title": "North or South? Diagnosing LLMs' Understanding of North Korean Language, Society, and Knowledge", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15277", "title": "Do correct answers have stable latent knowledge support?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15267", "title": "LeHami: Symplectic Latent Dynamics for World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15225", "title": "Zeroth-Order Fine-Tuning of LLMs in Learnable Low-Rank Subspaces", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15207", "title": "Exploring Jailbreak Vulnerability Across Depth-Based Dynamic Inference in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15205", "title": "MoSAIC: Learning DAG Scheduling Heuristics from Optimal Schedules through Motif-Aware Recovery and LLM-Guided Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15204", "title": "SocraticRepair: Planning-Guided Socratic Tutoring for Program Debugging and Misconception Repair", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15203", "title": "Do LLMs differentiate linguistic traits internally?: A layer-wise analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15179", "title": "UDHRBench: Benchmarking Human Rights in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15177", "title": "Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15171", "title": "LexiCan: Lexicographic Canonicalization of Point Clouds for Machine Learning Applications", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15159", "title": "Beyond Adjacent Layers: Graph-Guided Layer Fusion for Compressing Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15154", "title": "Where Did We Go Wrong? Localizing Errors to Repair Multi-Turn Conversations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15139", "title": "When Dynamic Scaling Fails: A Scale-State Feedback Governs Recurrent-State Quantization in Linear-Attention and SSM LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15128", "title": "To Defer or Not to Defer? Online Learning with LLMs and Congested Experts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15124", "title": "ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15103", "title": "RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15098", "title": "TIDE: Trajectory-Informed Skill Distillation for Efficient Text-to-Video Prompt Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15097", "title": "Anchors Enhance Controllability and Reasoning of Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15095", "title": "Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15093", "title": "TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15091", "title": "Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15058", "title": "The Optimal Decoder is Tilted Temperature", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15056", "title": "Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15044", "title": "PAT: A Personality-Driven Augmentation and Transfer Learning Framework for Depression Detection on Social Media", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15043", "title": "Information-Theoretic Foundations of Online Temperature Sampling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15029", "title": "Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15028", "title": "UltraBERT: Beyond the Limit of BERT Pre-Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15005", "title": "Retraining-Free Depth Pruning of Vision Transformers: A Cross Domain Study of Layer Redundancy", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14976", "title": "Metric-Driven Reinforcement Learning for Object Hallucination Reduction in LVLM-Based Image Captioning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14971", "title": "HodgePhaseNet: Discrete Hodge Decomposition of Semantic Flows in Transformer Attention", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14968", "title": "SEEK: Agentic Knowledge Graph Retrieval for Secure Code Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14961", "title": "HiPAD: A Unified Gait, Audio-Visual, and Personality Fusion Network for Depression Detection, with a Hierarchical Personality Ablation and the Calibration Limits of Domain-Adapted LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14958", "title": "What Survives When Activation Steering Is Used as Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14952", "title": "Do Personalized LLMs Need the Whole Conversation? Matching the Full History with Only 5% of Its Text via Relevance-Filtered Context", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14937", "title": "Predicting how model propensities generalize out of distribution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14936", "title": "CFG-Policy: Unified Diffusion Policy Learning Framework via Classifier-free Guidance", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14923", "title": "TLA-Verus: Generating and Solving Temporal Proof Obligations with LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14921", "title": "Representation Drift in Continual Learning: LoRA versus N-gram Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14913", "title": "Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14896", "title": "Test-Time Compute for Humanoid Behavior Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14883", "title": "MARL-BattleGrounds: A Novel JAX-native Benchmark for Heterogeneous and Competitive Multi-agent RL", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14879", "title": "Social Bias in Chinese Large Language Models under Social Media Expressions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14873", "title": "Dependency Reasoning for Aspect Sentiment Quadruple Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14871", "title": "MORE: Learning Motion-Oriented Registers for Driving World Models and Planning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14860", "title": "Terrarium: Growing Personal Assistants via Scalable Synthesis of App Worlds", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14802", "title": "YOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14789", "title": "Training-Free BioNEL-RAG: Advancing Biomedical Entity Linking through Retrieval-Augmented Generation and Large Language Model", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14769", "title": "Who Receives Respect? A Counterfactual Benchmark for Honorific Allocation Bias in Bengali", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14763", "title": "CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14756", "title": "Amharic-English Cross-Language Question Answering Using Statistical Machine Translation, Named Entity Recognition, and Semantic Indexing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14746", "title": "BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14720", "title": "CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14710", "title": "DeKoR: Decomposed Knowledge Routing for Efficient GNN--LLM Fusion", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14701", "title": "Towards Merging-conditional Backdoor Unalignment against Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14691", "title": "DexCast: Learning Real-World Dexterous Control from Human Videos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14688", "title": "Accelerating Cross-Model LLM Inference via Attention Map Reuse", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14687", "title": "One-Way Coupling via Patchwise Adaptive Normalization in Transformer Surrogates", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14683", "title": "Triage-PiEvo: Evidence Admission for Principle-Evolving Scientific Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14680", "title": "A Hybrid Kinematic GCN and Elastic Transformer for Efficient Indian Sign Language Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14671", "title": "SPARE: Shared Perception and Adaptive Retrieval of Evidence for Streaming Video Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14651", "title": "TAG: Calibrating SAM3 for Universal Image Segmentation without Dense Supervision", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14647", "title": "Can Synthetic UAV Benchmarks Be Trusted? Real-Synthetic Validation for UAV Model Selection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14635", "title": "PVFH-Bench: Benchmarking Premise-Induced Visual Fixation Hallucinations in Vision-Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14626", "title": "TagBO: LLM-Driven Task-Aware Graph Bayesian Optimization for Scientific Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14612", "title": "LLM-Augmented Bayesian Optimization with Adaptive Policies for Chiplet Design Space Exploration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14605", "title": "Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14589", "title": "Attribute-Centric Vision-Language Alignment for Fine-Grained Gait Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14588", "title": "Flow-Support-Weighted Proposals for Test-Time Verified VLA Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14578", "title": "Uniform Information Density-Based Preference Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14571", "title": "Dissecting the Carbon-SLO Tension in Geo-Distributed LLM Serving", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14531", "title": "LongHisDoc: A Comprehensive Benchmark for Chinese Long Historical Document Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14519", "title": "Query-Adaptive Neuron Steering for LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14475", "title": "EdgeLLM-Nano: Auditing Polar-Guided Key-Cache Compression and Consistency-Anchored Pruning on a 33.6 MB On-Device Language Model", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14460", "title": "Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14442", "title": "Evaluating Semantic Relation Knowledge through Bidirectional Relation Prediction from Gloss Pairs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14438", "title": "Neither True nor False: Do LLMs Represent Truth-Value Gaps in Plural Predication?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14436", "title": "Design Choices for Multimodal Transformer Learning with Missing and Longitudinal Healthcare Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14431", "title": "MemForm: Benchmarking Memory Formation Poisoning in LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14427", "title": "ByteMark: A Unified Byte-Level Watermark for Detection Across Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14423", "title": "Scaling Laws for Multimodal Data Mixtures", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14413", "title": "Coarse-Graining Recursive Expert Computation: Continuation-Relative Interfaces and Failure Modes", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14406", "title": "Memory Without Curation: Learning Multi-Stream Latent Memory for Robot Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14405", "title": "SPROUT: Scaling Agentic Reinforcement Learning for Long-Horizon Software Engineering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14400", "title": "Sparse-TD-JEPA: Improving Zero-Shot Reinforcement Learning With Sparse Latent Task Representations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14397", "title": "RealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14393", "title": "SciCurateBench: Curating Experimental Data from Heterogeneous Scientific Literature with Verbal-Action Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14385", "title": "Deep learning from a control vantage point", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14378", "title": "Tokenization-Invariant Watermarking: A Byte-Local Method for LLM Text", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14351", "title": "Learning Transferable World-Action Models from Task-Paired Human Videos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14349", "title": "Multimodal Co-Generation With Continuous Bitstream Diffusion", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14346", "title": "Evaluating LLMs as Agentic Workflow Executors in Real-World Customer Support Skills", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14344", "title": "On the Depth Transfer of Neural Optimizers via L-Smoothness", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14334", "title": "Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14324", "title": "EV-JEPA: Elastic V-JEPA for Any Device and Cross-Device Inference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "ev-jepa", "detail_path": "reproductions/2610.14324-ev-jepa/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.14309", "title": "ASSET: Adaptive Speech Segmentation via Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14299", "title": "RUBATO: Decoupled Clocks Allow Full-Duplex Models to Think as Fast as They Can", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14277", "title": "Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14270", "title": "The Thinking Leakage in Reinforcement Learning for LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14265", "title": "Thinking with Images without Coordinates", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14238", "title": "Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14228", "title": "Latent World Action Model for GUI Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14226", "title": "CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14224", "title": "Harness^2: Recursive Agent Harnessing for an Open World", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "harness2", "detail_path": "agent-research/2610.14224-harness2/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.14214", "title": "Embedding Graph Kernel Entropy (EGKE): Fine-grained Hallucination Detection for LLMs from Embeddings", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14212", "title": "Modeling the Arrival Time of Information-Bearing Events in Natural Language", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14196", "title": "Simple Linear Corrections for Compression in Late Interaction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14180", "title": "Unconstrained CTI-REALM with Open-Weights", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13925", "title": "Can machines reason non-verbally?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13917", "title": "Designing Protein Structures from Natural Language", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13910", "title": "When VLMs Destroy What They Know: Spatial Representations Fall Below Lexical Priors", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14162", "title": "Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14159", "title": "Disentangling Task-Relevant Latent Dynamics for Reward Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13858", "title": "LapMerge: Differentiable Exact-Budget Token Merging in Linear Time", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13840", "title": "Studying Comics at Scale with Artificial Intelligence: The PAGE Framework and Three Studies of American Comics and Japanese Manga", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14155", "title": "Axiom-0: Hierarchical Self-Refinement for Vision-Language-Action Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13834", "title": "On the Design Space of Continuous Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "doublecat-semicat", "detail_path": "reproductions/2610.13834-doublecat-semicat/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/doublecat-semicat-a30-20261013.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13832", "title": "SpatialASM: Internalizing Active Mentalization for Spatial Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13811", "title": "QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13810", "title": "Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13797", "title": "REFLECT: Role-Aware Detection of Sentiment, Emotion, Politeness, and Formality", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13794", "title": "Not Just an Evaluation: A Case Study of Discourse Particle Sensitivity in Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13790", "title": "OccludeBench: Can VLMs Find What's Missing?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13783", "title": "UkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian Memes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13781", "title": "SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13778", "title": "ReplaySSM: Cache SSM Inputs, Not State", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "replayssm", "detail_path": "reproductions/2610.13778-replayssm/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/replayssm-a100-20261013.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13767", "title": "DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "dualquant", "detail_path": "reproductions/2610.13767-dualquant/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-dualquant-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13763", "title": "Neurons++: A Unified Visual-Stream Framework for Image and Video Reconstruction from fMRI with Neural-to-Visual Interpretability", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13755", "title": "Matched-Context Group Policy Optimization for LLM Agent Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13740", "title": "SmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge Devices", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "smolwam", "detail_path": "reproductions/2610.13740-smolwam/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct13-smolwam-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13735", "title": "Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "orthros", "detail_path": "reproductions/2610.13735-orthros/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-orthros-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13708", "title": "Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13697", "title": "Improving Semantic Coverage in AI Test & Evaluation through Generative Augmentation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13695", "title": "Verifiable Retrieval for Legal Reasoning through Structure-driven Knowledge Graph", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13690", "title": "Transformer-based In-Context Score Operator Learning for Diffusion Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13672", "title": "Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "upturn", "detail_path": "reproductions/2610.13672-upturn/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.13663", "title": "A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13660", "title": "Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13653", "title": "A Critical Look at Power Sampling when Test Time Sharpening LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13643", "title": "DexBioLab: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13636", "title": "Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question Answering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13635", "title": "PANDA: Prior-guided Attentional Dual-path Architecture", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13627", "title": "AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13617", "title": "Training User Simulators with Latent Intrinsic Feedback", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13605", "title": "zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14138", "title": "Exploring the Latent Structure of AMD Severity Using Retinal Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13578", "title": "RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13563", "title": "Not All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue Resolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13557", "title": "Probabilistic Ship Trajectory Forecasting using Transformer Models on AIS Data", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13550", "title": "Personalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13548", "title": "Auditing VLM Benchmarks from Existing Evaluation Runs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13527", "title": "S-Space: Exploring Spatial Workspace in Multimodal Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13524", "title": "Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13510", "title": "Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13485", "title": "Proactive Agentic Orchestration", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13411", "title": "In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13386", "title": "MoPrO-SD: Modular Prompt Optimization for Stance Detection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13375", "title": "From Structure to Validity: Mechanism-Guided Generation and Refinement of LLM Rubrics", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13370", "title": "Overcoming Data Imbalances with Expert Selection Biases", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14124", "title": "The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13348", "title": "Test-Time Memory Construction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "t2mem", "detail_path": "reproductions/2610.13348-t2mem/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-t2mem-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13341", "title": "Understanding Mamba-3 Through Oscillatory Dynamics", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13337", "title": "Exploring Attention Sinks in Text-to-Image Transformers from Diffusion and Autoregressive Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13335", "title": "AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13334", "title": "PDE-PFN: Prior-Data Fitted Neural PDE Solver", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13330", "title": "Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13325", "title": "Taking Tokenization off the Host for Agentic LLM Serving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13321", "title": "Host-Aware Web Crawling for LLM Pretraining Data", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13315", "title": "JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13303", "title": "Agreement Without Alignment: Label-Free Rubric Clarification Increases LLM-Judge Consensus but Not Agreement with Humans", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13276", "title": "CopRoute: Dependence-Aware Conformal Routing for Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13272", "title": "OWLET: On-Policy Weighted Learning via Evidence Transfer for Video Large Language Model Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13264", "title": "CV-OPD: Contrastive Vision On-policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "cv-opd", "detail_path": "reproductions/2610.13264-cv-opd/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/cv-opd-a100-20261013.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13263", "title": "SheafPrune: Sheaf-Guided Graph Propagation for Visual Token Pruning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13262", "title": "Dual-Stream Memory for Vision-Language-Action Policies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13261", "title": "Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13259", "title": "Beyond a Single Crop: Contextualized Embeddings for Player Re-Identification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13253", "title": "Tabular Foundation Models Are Effectively Shallow", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13252", "title": "Vision Transformers Learn Word Meaning from Images Alone", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13239", "title": "Jag: Direct Box Prediction for Efficient Visual Grounding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13237", "title": "The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14118", "title": "ClawLoop: Self-Improving Agents via Harness-Native Training Loop", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13208", "title": "How Much Computation Does Every Forecast Need? Structured Block Skipping in Two Time-Series Foundation Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13207", "title": "SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13202", "title": "S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13171", "title": "PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13154", "title": "From Glance to Focus: Mitigating Recognition Laziness in MLLMs for Fine-Grained Recognition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13143", "title": "Measurable Semantic 3D Gaussian Splatting with Joint Region and Depth Supervision for Interactive Building Inspection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13128", "title": "Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13123", "title": "Why Heavy-Tailed Weight Spectra Predict Model Quality", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13117", "title": "Forward Dynamics Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13111", "title": "What Do Visual-Head Discovery Scores Actually Find? Attention Source, Necessity, and Random-Control Pitfalls in Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13106", "title": "Scaling RNA Foundation Models through Iterative Refinement", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13105", "title": "Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level Labels", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13102", "title": "From 2.1M Hours of Raw Broadcast Audio to Finnish Speech SSL: Confidence Filtering and Architectural Analysis at Scale", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13064", "title": "CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13060", "title": "KV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache Reuse", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13056", "title": "A4-MR: Abnormality-aware Anatomical Alignment for MR", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13045", "title": "Redirecting Teacher Supervision: Temporal-Response-Guided Latent Distillation for Video-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13041", "title": "RAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13040", "title": "Lightweight Time-Frequency Vibration Sensing for Consumer Device Condition Monitoring", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13035", "title": "GeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13024", "title": "What Visual Representations Do World Action Models Need?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13021", "title": "EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13020", "title": "Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "tapo-trajectory", "detail_path": "reproductions/2610.13020-tapo-trajectory/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.13015", "title": "Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "gppo-framework", "detail_path": "reproductions/2610.13015-gppo-framework/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.12998", "title": "Evaluating LLM Creativity through Long-Tail Performance", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12995", "title": "What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12987", "title": "Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12981", "title": "The Evidence Anchoring Boundary: Where Visual Interventions Matter and When They Help in Multimodal LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12975", "title": "SmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14112", "title": "Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional Languages", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "jev-regional-transfer", "detail_path": "system-one/2610.14112-regional-transfer/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.12961", "title": "MVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual Graph", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12959", "title": "Video Codec-Guided Training-Free Token Compression for Video Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12942", "title": "In-Context Learning Can Help Vision-Language Models Overcome Training Priors", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12939", "title": "Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12907", "title": "BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12898", "title": "Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12886", "title": "LeapBot-JAC: Joint Action Chains for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12874", "title": "Temporal Evidence Forests for Long-Horizon Multi-Party Conversational Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12866", "title": "CaptchaAgent: Verifiable Visual Reasoning for CAPTCHA Solving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12865", "title": "Robust Langevin Sampling under State-Dependent Heavy-Tailed Noise with Applications to LLM Fine-Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12864", "title": "Time Delay System for Sequence Modeling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12837", "title": "COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12828", "title": "TreeHCA: Hindsight-Guided Exploration and Credit Assignment for Multi-Turn LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12818", "title": "LeWAM: End-to-End World and Action Modeling with JEPAs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "lewam", "detail_path": "reproductions/2610.12818-lewam/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct13-lewam-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12813", "title": "VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12794", "title": "Meta-Reflective Evolution Effectively Improves Production AI Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12792", "title": "Large Language Models, Machine-Assisted Cultural Analytics, and the Agentic Turn", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12783", "title": "Shift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual Segmentation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12742", "title": "U4RASD at KnowledgeGraphEval-2026: Ontology-Constrained Encoder and LLM Systems for Arabic Relation Extraction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12734", "title": "StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12711", "title": "Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12707", "title": "Unsupervised Multimodal Reward Modeling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "umrm", "detail_path": "reproductions/2610.12707-umrm/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-umrm-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12703", "title": "Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12669", "title": "GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12668", "title": "Recurrent Harness for Agentic Continual Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12667", "title": "perturber: A Stateless Service for Semantics-Preserving Text Perturbations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12651", "title": "SynAct: Synergistic Active Feedback Learning for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12650", "title": "Feature Competition and Its Representational Origins in Vision Language Models: Evidence from the Stroop Paradigm", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12644", "title": "Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12617", "title": "GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12610", "title": "Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12602", "title": "Self-Preservation in Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12599", "title": "STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12596", "title": "SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14094", "title": "Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12582", "title": "One Model to Loop Them All: Elastic Latent Recurrence for Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12575", "title": "Mind the Temporal Gap: Evaluating Video Models for Temporal Understanding in Driving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12570", "title": "Contextual Correction of Parallel Drafts for Speculative Decoding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12545", "title": "AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12461", "title": "OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12458", "title": "OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12451", "title": "VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12445", "title": "Telling FIBS: Probes Effectively Detect Sabotage and Catch Unverbalized Deception", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12435", "title": "VioLA: Learning Generalist Humanoid Control Policies from Human Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12427", "title": "FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12417", "title": "WOVEN: Weaving Visual World Modeling into Multimodal LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "woven", "detail_path": "reproductions/2610.12417-woven/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-woven-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12410", "title": "Predicting Alignment Generalization with Value Representations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12407", "title": "LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12402", "title": "SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12390", "title": "Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12386", "title": "ARC: A Reasoning Recipe for Robot Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12382", "title": "WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12375", "title": "OnTrack: Real-Time Monitoring and Intervention in LLM Agent Trajectories via Streaming Structure-Aware Optimal Transport", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "ontrack", "detail_path": "agent-research/2610.12375-ontrack/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.12367", "title": "Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "sguid", "detail_path": "post-training/2610.12367-sguid/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/sguid-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12360", "title": "Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12355", "title": "Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12349", "title": "SplitJEPA: Learning Invariant and Variant Latent Worlds without Reconstruction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12345", "title": "Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12338", "title": "VFold: Symmetry-Aware Cross-Layer Value Cache Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "vfold", "detail_path": "foundation-models/2610.12338-vfold/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/vfold-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12327", "title": "SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "sparse-decoding", "detail_path": "foundation-models/2610.12327-sparse-decoding/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/sparse-decoding-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12325", "title": "Prior or Feedback? What an LLM Uses When Adapting Neural Operators", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12313", "title": "Verdict Without the Rule: Diagnosing and Auditing Regulatory Rule Sensitivity in LLM Compliance Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12310", "title": "Is In-Domain Training Enough for Fine-Grained Industrial Anomaly Understanding?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12305", "title": "From What to Which: Decoding Modifier Grounding in Frozen MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12285", "title": "PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12281", "title": "Unlocking the Regulatory Genome by ARGUS: An Evidence-Constrained Agentic Framework for Interpreting Single Nucleotide Variants", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12266", "title": "DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12248", "title": "EgoVoice: Proactive Spoken Assistance from Egocentric Multimodal Streams", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12242", "title": "TokenRouter: Efficient Serving System for Token-Level LLM Routing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12235", "title": "Language Models as AI Research World Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12231", "title": "Residual Modeling Closes the Regression and Generative Policy Gap in Robot Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12214", "title": "DiffuPlex: Accelerating Full-Duplex Spoken Dialog Models via Rolling Masked Diffusion", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12194", "title": "MiniWAM: Learning Compact Future Targets for Efficient World-Action Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12190", "title": "DataSense-Bench: The First Step Toward an AI Scientist", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12185", "title": "RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12183", "title": "A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12147", "title": "Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12144", "title": "Language-Specific Effects of Tokenizer Choice in Multilingual Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12137", "title": "Poster: A Preliminary Study of LLM Distillation Inference", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12133", "title": "Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12126", "title": "SuperNav: An Agentic Navigation System for Any Task in Any Scene", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12106", "title": "Could LLM Watermark Detection be Public?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12099", "title": "UNITAS: A 3D-Native World Action Model for Embodied Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12083", "title": "All Verdicts are Not Equal: Rethinking LLM Judge Reliability", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12064", "title": "ILM: An AI-Powered Storytelling Educational Tool", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12061", "title": "When Should Agents Think? Adaptive Reasoning via Cross-Turn Estimation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "race", "detail_path": "agent-research/2610.12061-race/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/oct10-race-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12060", "title": "Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "vimod", "detail_path": "multimodal-models/2610.12060-vimod/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/vimod-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12048", "title": "Do Not Train Away Uncertainty: Early Uncertainty Anchored Calibration", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12030", "title": "Natural Language to First-Order Logic LLM-based Autoformalization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12026", "title": "HWAM: Humanoid World Action Model With Joint State--Action Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12022", "title": "Examining Social Attribution in LLM Reasoning: A Theory-Guided Probing Methodology", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12002", "title": "Agentic-TTT: Training test-time policy for test-time training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11993", "title": "DataVista: Diagnosing Multimodal LLMs on Data Video Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11986", "title": "FearCaut-Qwen: Affective Steering in a Vision-Language Model Shifts the Decision Criterion for Hazard Assessment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11978", "title": "Specialized Decision Models vs. General-Purpose LLMs: Benchmarking Jev Across Knowledge, Reasoning, and Multilingual Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "jev-capability", "detail_path": "system-one/2610.11978-jev-capability/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/jev-capability-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11966", "title": "MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11959", "title": "MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11954", "title": "Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11948", "title": "When History Helps and Hurts: Selective History Use across Multimodal Turns", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11938", "title": "Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11924", "title": "Revisiting Identity and Spectra Dispersion in Media-Bridged Time Series Forecasting: Linking Multivariate Signals and Narrative Flows", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11920", "title": "Event-Centric Memory with Query-Aware Graph Augmentation for Long-Term Conversational Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11907", "title": "Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11901", "title": "Can Decision Models Understand Stance? Evaluating Jev Against General-Purpose LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11899", "title": "Forms of LLM-Integrated Applications from LLM-Chats to Autonomous AI Agent System", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14082", "title": "SenseWeather: Multimodal Sensing for Robust Robotic Perception under Extreme Conditions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12532", "title": "Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11845", "title": "Detecting Spin in Clinical Trials with Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11826", "title": "From Suppression to Repair: Mitigating Object Hallucination in Large Vision-Language Models via Localized Distribution Alignment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11818", "title": "From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11810", "title": "Seek-and-View Reasoning for Multi-View Spatial Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11794", "title": "Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "memento3", "detail_path": "agent-research/2610.11794-memento3/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/memento3-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11776", "title": "DPPM: Dual-Path Parametric Memory for Personalized Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11766", "title": "Same Outcome, Different Evidence: Intent Recovery in LLM Safety Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11765", "title": "Thinking Inertia: LLMs Keep Thinking When Told Not To", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11761", "title": "RAGenome: Scaling Retrieval-Based Genomic Language Models to Long Contexts", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11730", "title": "Spectral Weight Decay: Inducing Low-Rank Structure in Neural Network Weights", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11678", "title": "TRACE: Diagnosing Verifier Brittleness in Agentic Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11674", "title": "VESSI - VLM-Enhanced Support for Surveillance and Investigations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11655", "title": "Harness Evolution Hits a Ceiling: When Weight Training Should Begin", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11610", "title": "Beyond Report Imitation: Clinically Aware Multi-Image Ultrasound Report Generation from Visible Evidence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11605", "title": "NanoProof: Open and Efficient Automated Theorem Proving in Lean 4", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11599", "title": "Large Language Model Turnover Undermines Screening for Artificial Intelligence-Assisted Scientific Writing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11592", "title": "Probing for Long-Horizon Deductive Reasoning Capabilities in Language Models with Prolog", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11586", "title": "Measuring Cultural Alignment Beyond the Average: A Framework for Evaluating Maternal-Health LLM Interactions in Indian Contexts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11585", "title": "Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11578", "title": "Chronos Enables Code Agents to Reason over Software Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11567", "title": "Sera: Semantic Representation Aggregation with Knowledge and LLM for Reliable and Interpretable Battery Health Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11559", "title": "SWE-Journey: Towards More Realistic Evaluation of Coding Assistants through Long-Horizon, Multi-Turn Interaction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11548", "title": "Conditional Transfer from Controlled Pretraining Mixtures to Code", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11544", "title": "Prosody-to-Text: Predicting text from low-pass filtered speech", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11543", "title": "Learning the Loop, Not Just the Page: Execution-Grounded Loop Learning for Web Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11542", "title": "Constitutional Gating and Deterministic Recovery for Multi-Agent LLM Negotiation: Ablations Against a Stateful Adversarial Gatekeeper", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11510", "title": "Does Modern Standard Arabic (MSA) Dominate Arabic Dialects in LLMs? A Representation-Level Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11508", "title": "WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11482", "title": "Evaluating Local Language Model Agents for Reproducible Data Engineering: An Empirical Software Engineering Study of Mobility Workflows", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11469", "title": "SAGE: Sink-Aware Guided Emphasis for Visual Grounding in Vision-Language Decoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11464", "title": "Who Verifies the Verifier? Co-Evolving Inspectable Graders with Self-Improving Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11461", "title": "Beyond Speech Captions: Speech-Rewarded Style Planning for Conversational Text-to-Speech", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11454", "title": "Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11447", "title": "Closed-loop evaluation of LLM agents for embedded software development", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11430", "title": "BioBigBird: A Sparse Attention Model for Long-Range Dependency Processing in Biomedical Text", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11422", "title": "Causal-fate dynamics of unrealized influence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11401", "title": "WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11389", "title": "Fact over Fiction: Detection of Pathological Hallucinations in Sinhala-to-English Neural Machine Translation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11382", "title": "PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11374", "title": "Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11373", "title": "From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11371", "title": "SignRAG: Unified Retrieval-Augmented Gloss-Free Sign Language Translation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11363", "title": "UniData: Universal Multimodal Instruction Generation Pipeline", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11361", "title": "SepGen: Multi-Stem Audio-Video Separation and Generation in a Single Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11358", "title": "RaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11354", "title": "AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11351", "title": "Deception by Omission: Language Models Knowingly Hide Their Mistakes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11329", "title": "PathLang: A Language-Centered Benchmark for Vision-Language Models in Computational Pathology", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11317", "title": "DivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11316", "title": "MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "metaencoder", "detail_path": "foundation-models/2610.11316-metaencoder/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.11315", "title": "Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11314", "title": "From Retrieval to Reconstruction: Constructing Evolvable Cognitive Memory for Long-Term Dialogue", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11310", "title": "FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11303", "title": "Efficient Multi-Granularity Knowledge Transfer for Radiology Report Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11287", "title": "REMORY: Learning Residual Memory for Context Compaction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11283", "title": "Being-M0.7: A Latent World-Action Model for Humanoid Robots", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11281", "title": "How to post-train on a surrogate: Envelope sampling mitigates reward hacking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11270", "title": "Gated Memory: Admission-Controlled Memory Formation for Conversational AI", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11251", "title": "V-CoLA: Vision Token Compression with Linear Attention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "vcola", "detail_path": "multimodal-models/2610.11251-vcola/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/vcola-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11245", "title": "Read What Matters: Query-Adaptive Quantization for KV Caches", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11231", "title": "Harness Compilation: Which Decisions Should a Small Vision-Language Model Keep?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11226", "title": "When Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11216", "title": "The Lattice of Transition Laws", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11214", "title": "Bridging KV-Cache Quantization and Linear Attention: From Theory to Pretrained Weight Migration", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11205", "title": "Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11196", "title": "Selective Listening: Mechanism-Guided Control of Audio Influence in Large Audio-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14074", "title": "One Model, Multiple Compute Budgets: Multi-Ratio ConceptMoE for Flexible Compute Across Turns", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14073", "title": "Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11161", "title": "VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11160", "title": "LadderEdit: Edit-Level Residual Compression for Memory-Efficient Lifelong Editing of LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11159", "title": "Local Prototype Reconstruction for Text-Compatible Speech-to-LLM Bridge Pretraining", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11148", "title": "SP-DocReader: Difference-Aware Self-Play for Precise Document OCR", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11146", "title": "When Do External Priors Help Low-Resource Structured Prediction? A Ranking-Level Alignment Study", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11144", "title": "Improving Image-Based Nutrition Estimation Through Multimodal Food-Item Verification and Recovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11140", "title": "ActiveMedAgent: Cost-Aware Trajectory Learning for Multimodal Medical Diagnosis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11136", "title": "The \"10th Juror\": Open-Set Standpoint Screening for Bureaucratic Bias Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11135", "title": "Can a System-One LLM Perform Knowledge Tracing When Few or No Learners Are Logged?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11132", "title": "SFT-as-Context Mitigates Forgetting in Supervised Fine-Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11113", "title": "DiscoVL: Unveiling Disentangled C ross-Modal Representation Learning via Orthogonal Adversarial Regularization for V ision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11076", "title": "Stability-Plasticity Balance via Singular-Vector Selection in LLM Continual Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11069", "title": "Clinician use of language models diverges from how the models are evaluated", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11067", "title": "Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12522", "title": "MolP2SBench: Do LLMs Really Reason from Molecular Properties to Structure?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11060", "title": "AffordDrive3D: Affordance-Aware World-Action Modeling with Spatial Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11039", "title": "Rendering-Free Lookahead for Question-Guided Active Vision", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11033", "title": "FedAlphaEdit: Null-Space-Aligned Merging for Collaborative Knowledge Editing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11019", "title": "Mid-Training Language Models on Raw Video", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "multimodal-models", "key": "raw-video-midtraining", "detail_path": "multimodal-models/2610.11019-raw-video-midtraining/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.11015", "title": "Prompts versus Rules: Auditing and Controlling Speech Naturalness Behaviors in Voice User Simulators", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11007", "title": "Curating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14071", "title": "Loose Lips: Understanding Privacy Leakage in Agentic Dialogue", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10990", "title": "Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10988", "title": "Back in Style: A Sociolinguistic Approach to Authoring and Measuring Persona Fidelity in User Simulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10984", "title": "Fluid-Gen-Zero: Grounding Pretrained Video Generators in Physics without Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10974", "title": "Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10971", "title": "When Citations Mislead? A Claim-Level Benchmark for Legal Hallucination Detection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10952", "title": "SPD-MetaFormer is what you need for small-data brain decoding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10946", "title": "AI4Fire: Evaluating Large Language Models on Wildfire Tasks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10942", "title": "StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10918", "title": "Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10912", "title": "When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10893", "title": "Less from More: Reinforcing Sparse Video Reasoning from Dense References", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10889", "title": "SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10871", "title": "Sparse Attention Is Matrix Approximation, Not Choosing from a Bag of Values", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10868", "title": "Conversational Voice Aesthetic Model with Reinforcement Learning from Human Listeners", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10858", "title": "RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10855", "title": "OmniHOI: Dexterous Hand-Object Interaction from Monocular Human Video", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10854", "title": "KDFP: A first-principles approach to knowledge distillation in large language models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10848", "title": "Amortized Off-Policy Evaluation for LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10845", "title": "Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12517", "title": "TerraAgent: Demonstration-Grounded Multi-Agent Reasoning for Long-Context Remote Sensing Visual Question Answering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10833", "title": "On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12516", "title": "TraceICL: Thread-Resolved Demonstration Curation with Consistency Calibration for Robust Multimodal In-Context Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10809", "title": "Evaluating Rubric Generation with Interventional Transfer", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10787", "title": "NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10786", "title": "Plan-and-Patch: Diffusion Language Models for Agentic Planning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10782", "title": "VICO: Visual Environments Co-Evolving for Vision-Language Model Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10760", "title": "DOGS: Design-Space Sampling for Prompt-Driven Logo Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10738", "title": "Lossy Compressive Text Autoencoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10697", "title": "On linearity or non-linearity in machine learning for quantum chaotic dynamics", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10533", "title": "EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10528", "title": "Long-WAM: Scaling the Context of World-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10526", "title": "Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10520", "title": "Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10515", "title": "RoboJEPA: Scaling Robotic Latent World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10506", "title": "Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10491", "title": "Insights from Autoresearch for Solar Panel Segmentation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10455", "title": "PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10448", "title": "MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive Screening", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10444", "title": "RunningTab: Direct Workspace Interaction with Environment-Side Tabs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10436", "title": "Detecting Adversarial Images through Response Profiles of Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10400", "title": "Self-correction Optimization for Interleaved Multimodal Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10395", "title": "Executing Causal Structure Learning with Linear-Attention Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10394", "title": "Kernel Autoresearch for Open-Ended Model Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10390", "title": "Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10385", "title": "OrBIT: Structure-Guided Embedding Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10384", "title": "OpenViTac: Learning and Benchmarking Visuo-Tactile Policies in a Unified Sim-and-Real Framework", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10378", "title": "Document-Level Text Simplification in Estonian Using Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10359", "title": "MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10655", "title": "Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10323", "title": "HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility Forecasting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10318", "title": "Nobody Truly Agrees on Sentiment: Humans, Bespoke Tools, and LLMs Struggle with Social Media Texts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10311", "title": "Fault-tolerant foundation models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10305", "title": "How Do Transformers Learn to Represent Symmetries?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10304", "title": "SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10650", "title": "Large Language Model-Assisted Preparation of Transportation Management Plans: A Case Study with WisDOT WisTMP System", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10286", "title": "$Δ$Representation: Geometry Supervised Representation Learning of Phenotypes via Counterfactual Reasoning for Medical VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10276", "title": "PatchBench: Measuring Collateral Damage in Activation Patching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10270", "title": "Video Prediction Policy 2: Predict Better, Act Better", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10238", "title": "Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10232", "title": "LLM Persuasion Is in the Eye of the Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10227", "title": "From Prompts to Trees: Effective LLM-Guided Tree Generation for Few-Shot Tabular Classification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10201", "title": "GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10199", "title": "Robust Decentralized Fairness Auditing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10179", "title": "Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10163", "title": "Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question Answering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10641", "title": "Coverage-Aware Reasoning with Medical Tokens for Diagnosis Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10156", "title": "HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10145", "title": "InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey Interviews", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10138", "title": "LLM4Impact: Integrating Heterogeneous Information for Scientific Impact Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10135", "title": "Attention via Black-Box Vector Search", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10636", "title": "D-SLR: The Disjoint Row-Sparse plus Low-Rank Decomposition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10118", "title": "YANchor-4B: Effective Long-Horizon Reasoning in O(N) Time with O(1) Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10114", "title": "Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10092", "title": "I would rather quit NLP than read another paper like this: The rise of antithesis in NLP papers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10085", "title": "Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10079", "title": "RealtimeWAM: How Fast Can I Run My World Action Model?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10068", "title": "Efficient Provably Private Classification with a Tabular Foundation Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10066", "title": "From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10058", "title": "Cache the Encoder Within:Compact, Reusable Memory across LLM Queries", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09985", "title": "Marrying Pricing and Advertising with LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09981", "title": "Sensitive-Topic Leakage Through LLM Routing Metadata: Measurement and Mitigation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09976", "title": "EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text Detectors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09969", "title": "TR-PTQ: High-Accuracy Integer-Only Transformer Post Training Quantization via Taylor Region Reformulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09952", "title": "MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09941", "title": "Purifying Backdoored Large Vision-Language Models by Removing Hijacked Directions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09940", "title": "Juno: Taming Predictive Latents for Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09920", "title": "Inverting Multi-Vector Visual Document Indices", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09919", "title": "Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09914", "title": "RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09907", "title": "FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot Classification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09872", "title": "LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09858", "title": "Training Advisors for LLM Agents from Task Outcomes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09841", "title": "ORCA: Hunting Compositional Failures in Text-to-Image Diffusion", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09835", "title": "A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never Speaks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09823", "title": "UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09802", "title": "DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09795", "title": "MIRROR: From Imitation to Internalization in LLM Personalization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09788", "title": "Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09778", "title": "Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression Testing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09772", "title": "Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09761", "title": "PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational Consistency", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09756", "title": "Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic Conditioning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09746", "title": "Flow-of-Thought: A Framework for Visual Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09742", "title": "SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul Videos", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09734", "title": "ΔWAM: Distilling Action Tangent Fields into World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09733", "title": "Bridge Routing Heads: Where Multilingual Multi-hop Reasoning Lives in LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09724", "title": "Towards Explaining Query Expansion Performance in Information Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09718", "title": "YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language Grounding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09710", "title": "SpikingVLA: Asynchronous Spiking Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09703", "title": "Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14063", "title": "Auditing LLM Program Search for Bermudan Stopping with Primal--Dual Certificates", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09700", "title": "What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10622", "title": "WorldBench: Evaluating LLMs on Three.js Voxel World Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09671", "title": "InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09661", "title": "Alice: A Large-Scale German Benchmark for Rubric-Based Multi-Dimensional Automatic Short Answer Scoring", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09660", "title": "Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09647", "title": "When Rank Rises as LLMs Degrade", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09624", "title": "How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09607", "title": "Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09597", "title": "COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10616", "title": "When Routing Reveals Membership: Privacy Leakage from MoE Router Telemetry", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09571", "title": "How Do LLMs Change Predictions Under Negation?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09569", "title": "RELATE: An Evaluation Framework for measuring Relational Orientation of Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09563", "title": "EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09550", "title": "Visual Evidence Under Cross-Examination: Evaluating and Controlling Decision-Level Evidence Use in Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09517", "title": "It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption Bank", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09514", "title": "STRIKE: Learning Visual State Transitions for Physical World Modeling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09513", "title": "OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09496", "title": "Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09489", "title": "Goldsmith: Gold-Loss-Guided Definition Optimization with an Agentic Annotation Harness", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09488", "title": "SiGNgapore - An Interactive Dataset for Sign-based Visual Navigation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09478", "title": "InstanceBench: Diagnosing Referential Reasoning and Target Identity in Referring Expression Segmentation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09476", "title": "CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model Engineering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09471", "title": "When Should an In-Context Learner Expand Its Hypothesis Space?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09467", "title": "Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented Languages", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09458", "title": "Right Number, Wrong State? Measuring Cross-Jurisdiction Substitution in LLM Recall of State Policy", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09457", "title": "DSReg: Provably Recovering Individual World Latents without Reconstruction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09446", "title": "Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09440", "title": "Mixture of Layers: Dynamic Layer Routing for Visual Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09430", "title": "SkillCycle: Co-Evolving Agent Policies and Skill Banks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09427", "title": "Event-Aligned Visual Action Reasoning for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09412", "title": "Finding the Right Balance: Relevance and Diversity in LLM Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09408", "title": "TiTok: Audio-Visual LLM for Multi-Segment Temporal Grounding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09392", "title": "Quantifying Volumetric Risk: Class-Aware Asymmetric Weighted Conformal Prediction for 3D Medical Image Segmentation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09384", "title": "The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09375", "title": "From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09371", "title": "The Confidence Game: Strategic Miscalibration in Human-AI Delegation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09360", "title": "TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09355", "title": "Multimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09346", "title": "OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09342", "title": "Shared Low-rank Basis Factorization for Data-free Mixture-of-Experts Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09337", "title": "Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09328", "title": "Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09321", "title": "Dialect-Robust Speech Language Models with Synthetic Pseudo-Dialect Augmentation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09313", "title": "Why VLMs Miss Small Objects, and When Zooming In Is Safe", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09311", "title": "Denoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token Realization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09276", "title": "CATune: Structural Constraint-Aware Bayesian Optimization for DBMS Configuration Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09252", "title": "Adaptive Visual Token Reduction for Accelerated Image Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09240", "title": "Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09239", "title": "The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09229", "title": "Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09219", "title": "CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09217", "title": "A Deterministic Evidence Layer for Vision-Language Autism Screening from Naturalistic Home Video", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09212", "title": "CurveTQ: Rotation-Free Trellis Quantization of LLM Weights via Curvature-Weighted Search", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09209", "title": "Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09205", "title": "Do Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09202", "title": "Few Bits, One Law: Toward W2A4KV2", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09194", "title": "Patient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09193", "title": "Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09186", "title": "The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09183", "title": "Q-PACE: Dynamic Precision Allocation for Quantization-Aware Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09179", "title": "LayerRoPE: Dynamic Depth-wise Magnitude & Angular Superposition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09152", "title": "sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09145", "title": "Noise Your Prompt: Noising Conditioning Tokens in Continuous Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09122", "title": "Are Parameter-Efficient Fine-tuning Methods Really Different?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09115", "title": "From Uncertainty to Action: Learning to Steer LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09096", "title": "Are We Really Benchmarking Forecasting Models? The Impact of Preprocessing on Time Series Performance", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09085", "title": "Anaximander: Interactively Running Geospatial Deep Learning Models on Any Compute Backend", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09079", "title": "Large-scale Repository Engineering via Agent-Native Reusable Code Primitives", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09074", "title": "TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09064", "title": "Talking with Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09063", "title": "Multi-Label Topic Assignment via LLM Distillation: A Comparative Analysis of Generative vs. Discriminative Student Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09058", "title": "Learning Cross-Model Activation Alignments with Explicit Many-to-Many Layer Maps", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09051", "title": "A Self-Pruning Transformer: Extreme KV-Cache Compression with Universal Attention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09048", "title": "Towards Financial World Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09027", "title": "Visual Memory Attacks Can Persist Through The KV Cache", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09015", "title": "Personalize at Test Time: Learning User Preferences for Image Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09003", "title": "Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08994", "title": "Phoneme-Guided Initialization for LLM-based Speech Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10594", "title": "Coverage, Not Difficulty, Sets How Much Synthetic Data an Activation Probe Needs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08963", "title": "On KL-Regularized Policy Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08959", "title": "GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08954", "title": "RACER: Reflective Agent Coupling Query Interpretation and Tool-Based Retrieval for Frame Selection in Long Video Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08941", "title": "SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08917", "title": "CARE: Certifying Acceleration for Vision-Language-Action Inference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08791", "title": "World Models' Last Exam in Physics", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08781", "title": "IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08779", "title": "ALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video Editing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08778", "title": "Sherpa: Teaching LLMs to Teach Adaptively", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08747", "title": "The Missing Minimal Pair: Stereotype Evaluation in LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08738", "title": "Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08718", "title": "When Forgetting is not Catastrophic: On the Mechanics of Spurious Forgetting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08716", "title": "Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08713", "title": "SpaTime: Streaming Vision-Language Models for Spatio-temporal Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08703", "title": "Agreement Is Not Validity: Cross-Model LLM Consensus in Diagnosing Student Failure Modes in K-12 Math Tutoring Dialogue", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08678", "title": "Secure Speculative Decoding for Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08675", "title": "Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08674", "title": "EC-RAG: Event Chain Retrieval-Augmented Generation for Long Video Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08670", "title": "Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08660", "title": "Evidence-Bound Reasoning: Neuro-Semantic Verification of Biomedical AI in Glioblastoma Radiogenomics", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08659", "title": "Selective Transfer of RL Updates for Visual Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08649", "title": "Stable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08647", "title": "SquidAgent: Parallelize Wisely, Coordinate Efficiently", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08640", "title": "RIWANav: Recursive World-Action Models with Self-Improvement for Urban Navigation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08639", "title": "Forensic Reserve: Eliciting Latent Knowledge for Image Forgery Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08630", "title": "Towards In-Parameter Memory Augmentation for Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08604", "title": "InterCorrect: Intersection-Aware Correction of Demographic Model Merging for Fair ASR", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08585", "title": "Large language models are vulnerable to incidental information in clinical documentation and reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08577", "title": "How Learning Governs Unlearning across the Memorization-Generalization Spectrum", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08560", "title": "Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08559", "title": "Latent space bias directions in LLMs capture confidence, not fairness", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08544", "title": "How High Is 0.6? Floors, Ceilings, and Headroom in Interpretability Probing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08539", "title": "RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08528", "title": "MedCORE: Criteria-Grounded Clinical Reasoning for Interpretable Medical Image Diagnosis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08526", "title": "WareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart Warehouses", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08513", "title": "Wiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World Discussions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08482", "title": "Knee3DVLM: Dual-Sequence Full-Volume Vision-Language Modeling for Comprehensive Knee MRI Assessment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08463", "title": "UNREAL: Unifying Retrieval and Long-Context with a Single Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08452", "title": "Agentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08414", "title": "Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08413", "title": "Knowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification Signals", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08403", "title": "SSR: Sparse Segment Reduction for Ternary GEMM Acceleration", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08402", "title": "VETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08401", "title": "GeoPID: Decomposing and Steering Visual Information in Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08400", "title": "Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08388", "title": "Foresight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question Answering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08341", "title": "DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08337", "title": "Machine Learning for German Redispatch Forecasting under Data Delays and Temporal Distribution Shift", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08331", "title": "Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08312", "title": "CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08303", "title": "Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08300", "title": "Memory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical Retrieval", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08268", "title": "DySCo: Dynamic Sharding for Collaborative Edge-Cloud LLM Inference with Depth-Synchronized Batching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08246", "title": "LeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility Proofs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08208", "title": "STRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficulty", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08200", "title": "Finding the Heads and the Neurons Responsible for Network Information Retrieval in Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08192", "title": "MacJEPA: Missingness-Robust Audio-Visual Recognition from Untrimmed Egocentric Videos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08183", "title": "Compact Robot Policies Need Fine-Grained Visual Representations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08164", "title": "Align, Then Correct: Training-Free Two-Stage Low-Rank Compensation for Extremely Quantized Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08162", "title": "The Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not Perception", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08161", "title": "Symphony for Text Generation: Benchmarking Clinical Note Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08153", "title": "Penalty-Framed No-Valid-Option MCQA: Analyzing LLM Abstention under Invalid Choices", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08133", "title": "VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08119", "title": "AutodidactWAM: Cross-Modal Self-Distillation from Generated Video to Robot Actions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08108", "title": "Enhancing Diffusion Language Models with Autoregressive Post-Training Weights", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08098", "title": "Surviving the Router: Optimizing Skill Injections for Retrieval and Execution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08095", "title": "Natural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-Healing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08093", "title": "SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08090", "title": "Explainable Rule Mining of IPv6 Extension-Header Presence Patterns from Paired-Vantage Captures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08085", "title": "DirectSpeech2LLM: A Simple End-to-End Framework to Mitigate Prompt Overfitting in Speech-LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08082", "title": "POLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08068", "title": "PhysTacGen: Physics-Aware Visual-Tactile Sensor Image Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08063", "title": "HINTT Submission to the 2nd MLC-SLM Challenge: Comparing Cascaded and Unified Approaches to Diarization and ASR", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08055", "title": "Language Carries the Expert's Impression: Instrument-Anchored LLM Judges Transfer Counseling-Quality Assessment and Beat In-Domain Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08048", "title": "DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08037", "title": "Are Language Models Script-Aware?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08026", "title": "The Labeling Problem in Hallucination Detection Benchmarks: An Empirical Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08018", "title": "Structured but Silent: Probing Capability Requirements in LLM Hidden States", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07990", "title": "A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07987", "title": "VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07982", "title": "M3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual Grounding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07969", "title": "EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07967", "title": "DecepEval: A Benchmark for Evaluating Deception in LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07966", "title": "Feature Encoding in VAE-based Audio Decoders: Effects of Input, Depth and Distribution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07954", "title": "Revisiting Numerical Forecasting Models for Language-Based Trajectory Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07948", "title": "Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07940", "title": "Hybrid Latent Attention for Looped Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07936", "title": "Pseudowords as probes: Large Language Models show little of the sublexical sensitivity that governs human pseudoword processing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07925", "title": "TF-PRVR: Training-Free Partially Relevant Video Retrieval", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07922", "title": "OpenWAM: An Open Framework for Composable World-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07913", "title": "Multimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide Images", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07904", "title": "ApexQuant: Data-Free Elastic Quantization by Residual Re-Isotropization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07903", "title": "Unsupervised Long-Tailed Adaptation of Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07894", "title": "Rethinking Faithfulness in LLMs: A Pairwise Context-Sensitive Perspective", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07887", "title": "Visual Abstention in Unified Multimodal Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08879", "title": "Tiny-Scale Chinese BERT Pretraining: A Controlled Comparison of MLM, WWM, and MacBERT Strategies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07868", "title": "CueRator: Agentic Search for Symbolic Rules to Adapt Frozen Multimodal Encoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07863", "title": "ReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07848", "title": "Dynamic Positional Attention Modulation for Parameter-Efficient Fine-Tuning of Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07847", "title": "OMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical Disagreement", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07832", "title": "Harness Engineering for Software Engineering via Modular Executable Dev-Primitives", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07825", "title": "Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07819", "title": "$α$Transfer: Coefficient Transfer for Efficient Model Merging", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07817", "title": "One Step at a Time: Trading LLM Autonomy for Process Predictability", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08875", "title": "An Empirical Study of Agent Skills' Downstream Utility", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07809", "title": "MASKerade: Token-Routed Mask Experts for Dense-to-MoE Upcycling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07782", "title": "Persistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can Tell", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07774", "title": "Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07767", "title": "TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07758", "title": "Later Is Better: Token Reduction for ViTs Under Distribution Shift", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07755", "title": "Trustworthy Method Comparison with AI Judges: Estimation and Design under Order, Batch, and Aggregation Effects", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07739", "title": "Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07729", "title": "Foveated Compression: Selective High-Resolution Preservation for Token-Efficient VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07723", "title": "The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07722", "title": "Does Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering Methods", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07706", "title": "WASD: Wasserstein-based Knowledge Distillation for Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07700", "title": "Detecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07699", "title": "Improving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07689", "title": "Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07681", "title": "EigenDEXplore: Structured Exploration for Dexterous Manipulation with Human Priors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07668", "title": "CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07657", "title": "Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07643", "title": "Monte Carlo Estimation for KV Cache Eviction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07625", "title": "Stateless Language Agents: Scaling Long-Horizon Automated Research", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07588", "title": "Personal-Agent Mediated Recommendation with Cross-Platform User History", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07587", "title": "Large Language Model Orchestration under Heterogeneous Preferences via Explicit Persona Inference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07585", "title": "REViT-v2: Hierarchical Windowed Roto-reflection Equivariant ViT for Equivariant Feature Extraction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07580", "title": "LOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07576", "title": "CETUS: How Far Do Representations Trained on Earth Transfer to Cassini SAR of Titan?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07572", "title": "Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07569", "title": "OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07563", "title": "HouseholdBench: Evaluating Large Language Models as Predictors of Household Economic Behavior", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07553", "title": "Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07540", "title": "Preserving Unstable Modes Through Inverse Dynamics in JEPA World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07535", "title": "Disentangling Models from Personas in Heterogeneous LLM Simulations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07533", "title": "SkillFormer: Skill-Decomposed Adaptation for Audio Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07532", "title": "Safeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark Knowledge", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07522", "title": "Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07518", "title": "Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07509", "title": "On Open-Ended Information Seeking for Information Elicitation Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07502", "title": "Closing Ambient Clinical Documentation Gaps with Automated Provider Queries", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07489", "title": "Deep Defence on Wheels: A Dual Intrusion Detection System Architecture for Comprehensive In-Vehicle Network Security", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07470", "title": "Structure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-Bandits", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07460", "title": "ElasticFit: Fit-Aware 3D Object Insertion via VLM Reasoning and Generative Adaptation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07457", "title": "AlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07426", "title": "AccentCL: Robust Accent Classification with Incremental Expansion", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07396", "title": "What the Elevation Map Cannot See: Semantic-Aware Locomotion and Execution-Aware Navigation for Humanoid Robot", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07389", "title": "Inference and learning in sparse autoencoders as natural gradient flow", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07385", "title": "Semantic Capability Acquisition and Specialization During Vision-Language Model Fine-Tuning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07365", "title": "Who Wrote It Is Not Enough: Detecting Who Contributed the Insight", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07362", "title": "Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07355", "title": "Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07349", "title": "RELACE: retrospective likelihood-based action credit estimation for long-horizon language agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07348", "title": "Stepped MoE: Segment-Level Routing with Configurable Inference Complexity", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07339", "title": "A doctrine-grounded visual question answering dataset for Tactical Combat Casualty Care", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07338", "title": "Logbook: Extremely Long-form Audio Event Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07335", "title": "Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07334", "title": "Weight Oracles: Reading Neural Network Weights with Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07332", "title": "Structuring MoE Expert Selection for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07324", "title": "Scale-Invariant Training for Time Series Foundation Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07306", "title": "Kurate: Scalable Scientific Quality Analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07269", "title": "What Words Keep of a Place: Zero-Shot Language Reasoning for Cross-View Geo-Localization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07258", "title": "Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07243", "title": "Hybrid Cross-Modal Attention Network for Early Breast Cancer Detection in Low-Resource Clinical Settings", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07209", "title": "Forecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation Triage", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07208", "title": "Can LLM-assisted regularization increase forecast accuracy for migration flows in low data regimes?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07168", "title": "A theory of platonic representations in language models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07132", "title": "CroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML Datasets", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06844", "title": "Learning to Read the Contextual Tokens in Diffusion Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06843", "title": "Recursive Video In-Context Learning for Agentic Robot", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06830", "title": "MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06825", "title": "PlotGround: Grounding Plot Digitization in Real Scientific Figures and Their Source Data", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06817", "title": "Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06814", "title": "TAPDreamer: Transferable Adversarial Patches for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06805", "title": "H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07127", "title": "PlaySuite: A Large-Scale Benchmark for Interactive Visual Intelligence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07125", "title": "Jailbreaking Open-Weight LLMs via Random Embedding Perturbations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06784", "title": "How to scale your HEP ML models: A recipe for robust architecture comparisons at scale", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07121", "title": "SoloQ: Calibration-Free Quantization for Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06750", "title": "Balancing Memory Pathways: Analyzing and Improving Memory Utilization in Hybrid LMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06748", "title": "BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06729", "title": "Improving Diversity in LLM Short Story Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06726", "title": "Decoupling Time and Space: A Temporally Conditioned Refinement for EEG Source Imaging", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07118", "title": "AMBER: Training Long-Horizon Web Agents through Append-Only Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06715", "title": "Domain adaptation of Russian ModernBERT for long legal documents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06695", "title": "MedPrune: Topology-Efficient Multimodal Multi-Agent Communication Evolution for Medical VQA Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06686", "title": "OVAL: Output-Aware Local Page Bases for KV Cache Retrieval", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06685", "title": "Aligning Multimodal Patient Evidence with Biomedical Knowledge Graphs for Clinical LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06670", "title": "Reward Stealing Attack on Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06666", "title": "What Matters for Latent Reasoning with Flow Matching", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06650", "title": "Wikidata Search Traces: A Dataset for Training Knowledge Graph Search Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06648", "title": "Representation-Space MMD for Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06647", "title": "LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06636", "title": "Differentially Private Mixing of Public Datasets Improves Private Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06625", "title": "JEV versus LLMs: Accuracy, Cost and Calibration on Seven Political Science Replications", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06617", "title": "RealtimeWAM: One-Step Asynchronous World Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06616", "title": "Video Encoders Built on Image Representations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "video-encoder-selection", "detail_path": "foundation-models/2610.06616-video-encoder-selection/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/video-encoder-selection-a100-20261021.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.06611", "title": "Lens3D: Target-Conditioned Visual Foveation for Fine-Grained 3D Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06603", "title": "Word-Level Text Unmixing via Evidence-Preserving Ownership Routing with Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07115", "title": "Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream Activations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06598", "title": "SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06587", "title": "Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06582", "title": "Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06576", "title": "Before Agent Tells The Lie: Has Deception Already Been Represented?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06571", "title": "BrainTRACE: Tracing Longitudinal, Multimodal, and Volumetric Evidence in Brain MRI Clinical Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07109", "title": "JudgeMoE: Distributional Aggregation for LLM-as-a-Judge", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06522", "title": "Anatomy of LLM Sycophancy: What a Flip Rate Hides", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06516", "title": "Test-Time Adaptation of Reasoning Strategies with Bayesian Nonparametric Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06514", "title": "ANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06513", "title": "SOL: Measuring Gaps between Text Distributions by Double Sliced Wasserstein Metrics", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06479", "title": "Behavior-Preserving KV Cache Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06446", "title": "The Assistance Dilemma: Learning to Teach via Multi-Turn Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06415", "title": "Training-Free Transformer Merging via Sequential Local Operator Alignment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06413", "title": "SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06409", "title": "FlashCart: Fast Cartesian Tensor Products for Equivariant Interatomic Potentials", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06406", "title": "What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06404", "title": "Quantifying the Stability of Multi-Step Reasoning via Error Amplification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06401", "title": "RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06394", "title": "Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06387", "title": "Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06366", "title": "Correct Verdicts, Flawed Reasoning: Structured Auditing of LLM-based Vulnerability Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06360", "title": "Ontology Concept Overlap as a Training Signal: Knowledge-Grounded Reinforcement Learning for Clinical Question Answering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06345", "title": "Breaking Bureaucracy: Evaluating open-source LLMs for legal document review", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06329", "title": "Dynamic Minimax Regret Optimization for Robust LLM Post-Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06324", "title": "Readout Blindness: VLM Scores Miss the Spatial Direction Their Frozen Encoders Retain", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07094", "title": "Evaluating Inference Compute for Generative AI: A Framework for Enterprise Workloads", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07091", "title": "Smart Content Ingestion for Generative AI Workloads", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06293", "title": "VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning for Video Event Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06286", "title": "DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06280", "title": "Future Anchored Verification and Online Recovery for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06273", "title": "Probabilistic Race and Ethnicity Prediction Using Group-Specific Name Lists", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06269", "title": "Evolving in Thought Space: Training a Small Model at Test Time Unlocks Better Discoveries", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07089", "title": "Towards a Unified Misuse Monitoring Benchmark", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06251", "title": "Shared Stopping Decisions Change Answers in HQQ Cache Quantization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06243", "title": "RoSA: Rotational Sparse Adaptation for Memory-Efficient Fine-Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06236", "title": "DP-ES: Differentially Private Evolution Strategies for Prompt Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06235", "title": "Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06226", "title": "LeAVJEPA: A Minimalist Architecture for Audio-Visual Self-Supervised Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06216", "title": "Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07086", "title": "SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06204", "title": "Do Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06196", "title": "EORestore-Agent: Fidelity-Guided Agentic Restoration of Remote Sensing Images with Composite Degradations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06174", "title": "Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06170", "title": "MS-Exam-Gen: An Automatic Benchmark Construction Toolkit for Evaluating LLMs on Multiple Sclerosis-MRI Imaging Knowledge", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06161", "title": "Introducing Code-Switched Contexts to Cognitively-Inspired Bilingual Model Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06147", "title": "Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06116", "title": "ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06100", "title": "From Traces to Agentic Worlds: Agentic Language World Models for Interactive Environment Simulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06093", "title": "Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06069", "title": "Attention Tax, Handoff Tax: A Stylised Model of When Multi-Agent LLM Systems Help", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06064", "title": "TrustMI: Causally controlling how assistants trust their users", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06063", "title": "Vision Transformer Ensembles for Panoramic Street Segmentation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06056", "title": "ROT: Rotating Hidden States towards Contextual Vectors for Hallucination Mitigation in LVLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06049", "title": "Backdooring Sparse Autoencoders", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06039", "title": "MercerFlow: Flow Matching in a Kernel-Induced Latent Space for Probabilistic Forecasting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06026", "title": "Differentiable Bit-Widths: Co-optimizing Pruning and Quantization via SVD for Ultra-Efficient LLM Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06021", "title": "Scalable Minimal-Change Learning for Controllable Image Editing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06018", "title": "Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06011", "title": "D-Loop: Looped Diffusion Drafting for Speculative Decoding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06008", "title": "Ultrasound Operator Guidance Using World Modeling and Retrieval Based Action Planning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08858", "title": "LRCC: Generalizing Low-Rank Compression with Conditional Computation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05996", "title": "EpicWorldModel: Exploration-driven Planning with Latent World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07070", "title": "Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05993", "title": "From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image Retrieval", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05982", "title": "Breaking the Tie: A Cluster-Aware Routing Framework for Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05978", "title": "Byte Language Models: Scaling, Emergent Abstractions, and Information Allocation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05977", "title": "StagQ: Constraint-Driven Multi-Precision Weight Quantization for LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05966", "title": "HuatuoGPT-3: RL-Only Domain Adaptation from Base Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05950", "title": "Discovered, Not Designed: Population Evolution for Collaborative and Compute-Intensive Model Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05940", "title": "ReMem: Streaming Video Understanding With Long Context Retention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05898", "title": "Collaborative Personalized Preference Alignment for LLMs under Data Deficiency", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05897", "title": "Fitting Vision Adapters at Frontier Scales", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05896", "title": "TasteRoute: Personalized Routing for Video Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05894", "title": "Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05885", "title": "The Optimization Landscape of Learning Compacted Context Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07062", "title": "Learning to Simulate Individuals from Macro Social Signals", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05879", "title": "Learning to Learn a Language", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05874", "title": "Global Communication or Graph-Specific Memory?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05872", "title": "Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07060", "title": "Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05863", "title": "CCQ: A Multi-State Child Care Quality Dataset to Support AI for Children's Health Research", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05861", "title": "Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05842", "title": "HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05833", "title": "Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05778", "title": "MedicalHarness: A Controlled Evaluation of LLMs and Agent Harnesses on Medical Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05774", "title": "AdaSpark: Adaptive DSpark with Online Learning for Tree Verification and N-gram Fill", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05744", "title": "CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05732", "title": "PACMI: Provenance-Aware Cascading Memory Invalidation for Long-Term LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05731", "title": "T-JEPA: A Temporal Joint-Embedding Predictive Architecture for Learning Better Remote Sensing Representations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05715", "title": "Rotated, but How Far? Diagnosing and Improving Object-Rotation Reasoning in VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05690", "title": "Errors of LLM-Assisted Literature Retrieval in Environmental Science: A Comparison Study of Abstract versus Full-text Based Prompts", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05685", "title": "Spend Bytes on Breadth: Precision-Count Trade-offs for Decode-Time KV Compression in Long Chain-of-Thought Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05681", "title": "Automatic Speech Recognition for Low-Resource Sinhala: A Critical Review of Methods, Challenges, and Future Directions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05664", "title": "StageVLN: Spatial and Trajectory Auxiliary Guidance for Efficient Vision-Language Navigation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05637", "title": "Visual Grounding Safety in Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05630", "title": "Atomic Visual Entailment: Enhancing Zero-Shot Vision-Language Reasoning through Atomic Fact Decomposition and Learned Selection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05615", "title": "DREAM: Dynamic Resolution Assignment For Multimodal Multi-agent Debate", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05600", "title": "An LLM-in-the-loop RL Framework for Bioinformatics Feature Selection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05591", "title": "What Is a Repeated Token Worth? The Scaling Geometry of Multi-Epoch Pretraining", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05590", "title": "ColdDDI: Evaluating Knowledge Utilization in Cold-Start Drug-Drug Interaction Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05584", "title": "Expanding LLM Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05572", "title": "Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05564", "title": "Lend Me Your Eyes: Instruction-Aware Text Embeddings via Attention Relay", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05541", "title": "Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05540", "title": "SALUS: Automated Auditing of NL-to-SQL Benchmarks through Weak Supervision of Multi-Agent Output", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05538", "title": "LiFT: Loop Flow Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05534", "title": "Dataset Signatures in Human-LLM Interactions and User Modeling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05484", "title": "Universal Test-Time Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05483", "title": "FLEX-WAM: Flexible Block-Causal World-Action Models for Long-Horizon Imagination and Planning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05463", "title": "Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07032", "title": "Investigating Model Compression for Neural Machine Translation in the Biomedical Domain", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05452", "title": "VERA: Verdict-Conditioned Reliability for Adaptive LLM Judges", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05450", "title": "Groupwise Distortion Guarantees for Preference-Based Alignment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05425", "title": "Unmentioned Checklist Findings Change How Reinforcement Learning Appears to Improve Chest Radiograph Report Checking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05418", "title": "EvoMem-VLA: State-Evolution Memory for Long-Horizon Robot Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05417", "title": "Render to Reason: Novel-View Semantic Prediction Improves Spatial Understanding in VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05413", "title": "A Strong Baseline for Evaluating Vision Encoders in Multimodal Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05409", "title": "BeliefGraph-JEPA: Structured Latent World Models for Action-Conditioned Time Series", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05402", "title": "Task Vector Descent: Learning from Non-IID Batches", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05400", "title": "CASE: Cost-Aware Stopping for Efficient Long-Video Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05387", "title": "GNN-CB: A Graph Neural Network Competition Benchmark for Human and LLM Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05380", "title": "VHDL-REPOBENCH: A Repository-Level Benchmark for Evaluating Large Language Models on VHDL Design Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05378", "title": "Distributed Subliminal Learning: Replacing Model Updates with Random-Carrier Outputs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05373", "title": "Towards Unbiased On-Policy Distillation for Block Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07025", "title": "WiSPER: Pose-Supervised Predictive and Residual Flow Refinement For Multi-Person 3D Pose Estimation With WiFi CSI", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05367", "title": "AIProver: Agentic Auto-Formalization of Mathematical Research via Certificate-Driven Evolving Harness", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05346", "title": "Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05342", "title": "IRSTD-Agent: Agentic Infrared Small Target Detection via Zoom-Guided Interaction Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05334", "title": "AgentDiscover: Autonomous Discovery with Minimal Search Scaffolding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05329", "title": "Understanding the Weight Averaging Mechanism in LLM Training for Post-Training Quantization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07023", "title": "Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05318", "title": "Robust Parameter-Efficient LLM Adaptation on Analog Hardware", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05308", "title": "RubricArmor: Adversarial Evolution Improves LLM-Based Rubric Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05306", "title": "Kinematics-Centric Continuous Sign Language Retrieval with Gloss-Guided Boundary-Aware Alignment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05305", "title": "Characterizing Parallelism Strategies in LLM Inference: Fundamental Compute-Communication Trade-offs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05303", "title": "ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05292", "title": "Erased, Rerouted, or Rescaled? Post-Training and the Causal Quotient of a Language Model's Belief State", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05275", "title": "Inductive Claims Extraction at Scale", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05274", "title": "Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05273", "title": "When and What to Prune? Stage-Aware Visual Token Pruning for Efficient VLA", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05249", "title": "ArticuTable: Generating Instance-Level Interactive Rigid-Articulated 3D Tabletop Scenes from a Single Image", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05247", "title": "templar: agentic induction and evolution of standardized radiology reporting templates from large-scale clinical corpora", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07014", "title": "DTFormer: Text-Guided Semantic Alignment for RGB-D Segmentation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05223", "title": "Look Before You Leap: Thermodynamic Arbitration of Parametric and Non-Parametric Knowledge in LLM Agents via Self-Regulating Memory Architectures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05200", "title": "Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05190", "title": "FORGE: Verification-Gated Behavioral Repair for Generative Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05185", "title": "Recurrent Latent Visual Search for GUI Grounding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07006", "title": "STOCK-JEPA: Prior-Anchored Latent Revision Representation Learning in Equity Markets", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05180", "title": "VICON: Visual-Inertial-Contact based Hand-Object Tracking for Manipulation Datasets", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05139", "title": "Hidden in the Comments: A Context-Injection Attack Surface in Code LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05131", "title": "RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05129", "title": "Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05126", "title": "Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05125", "title": "Bayesian Entropy-based Reordering for Calibrated Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05114", "title": "Belief-Trajectory Energy: Measuring the Path to a Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05111", "title": "InstMoE: Adaptive Multimodal Routing with Specialized Experts", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10571", "title": "SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05100", "title": "METRO: Metric-Enhanced Token Routing Operator", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05097", "title": "ReMAP: Restoring the Perceptual Cycle with Reasoning-Time Latent Visual Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05094", "title": "How Much Do LLM-as-a-Judge Design Choices Matter? A Systematic Comparison of Prompt Designs, Rating Scales, and Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05077", "title": "How Execution Assumptions Change Short-Horizon Sharpe Rankings: Evidence from a Synthetic Trading Benchmark", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05069", "title": "Usage-Modulated Sentiment Representations in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05066", "title": "Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05041", "title": "Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05039", "title": "Causal Improvement Graph for Agentic Harness Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06996", "title": "Mask-Guided KV Cache Eviction in Block Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05031", "title": "When LLMs Sit Above Diagnostic Tools: Unrealized Complementarity in Industrial Fault Diagnosis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05029", "title": "SPACE-CLIPv2: Decoding Local Geometry from Frozen CLIP for Monocular Depth Estimation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05026", "title": "GeoBridge-VLA: Geometry-Aware Residual Adaptation for Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06993", "title": "DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05025", "title": "Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05024", "title": "LightVLN: Efficient Aerial Vision-and-Language Navigation with Compact Memory and History-Guided Local Aggregation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05023", "title": "Look Where You Say You're Looking: Self-Grounded Attention for Visual Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04976", "title": "Priced Guidance: Can Language Models Generate Future Research Ideas?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04974", "title": "IREA: Intermediate Representation-based Embedding Alignment for Normative RAG", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04973", "title": "TrajLong: Co-Designing Agentic and Long-Context Supervision for Mid-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04961", "title": "Building LLM Agent Systems the Deep Learning Way: From Modular Design to Architecture Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04957", "title": "Trinity: One Differentiable Physics for Training, Refining and Scoring Generative Floorplanners", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04956", "title": "From Overloaded to Guaranteed: High-Throughput Multi-SLO Enforcement for LoRA-Assisted On-Premise LLM Deployment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04928", "title": "Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04927", "title": "Assembling Insights for Agentic Machine Learning Engineering Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04918", "title": "Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04913", "title": "$R^2$-WAM: Repair-and-Reject Post-Training for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04893", "title": "SFlexRCA: Lightweight, Scalable, and Flexible Root Cause Analysis for IIoT Edge Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04888", "title": "No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04875", "title": "SpecFold: Folding Multi-Branch Redundancy for Faster Speculative Decoding in Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04867", "title": "Greedy Local Learning for Language Model Pretraining: Gaps and Objective Design", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04862", "title": "GitSwarm: Decentralized Compounding Inference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04851", "title": "CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04845", "title": "Which Preferences to Train On? End-to-End Multi-Objective Alignment with an Adversarial Preference Distribution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06977", "title": "Visual-Invariance-Augmented Feature Optimal Alignment for Transferable Adversarial Attacks against Closed-Source MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04824", "title": "Agent Behavior as Code: Efficient and Robust LLM Agents with Programmatic Specifications", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04805", "title": "ExStereo: Lifting 2D Vision-Language-Action Models to 3D with Explicit Stereo Representations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04792", "title": "Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04778", "title": "Repeated-Measure Leakage, Distribution Shift, and Reliability under Partial Observation in Patient World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04777", "title": "ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04756", "title": "When Is Enough Enough in Self-Evolving LLM Systems?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04753", "title": "More Value per Key: Asymmetric Sparse Attention for Faster LLM Decoding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06972", "title": "BoT-Feedback: Grounding Multimodal Reasoning in Biomechanical Evidence for Explainable Human Action Feedback", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04737", "title": "PyINE: A Framework for Scalable Elicitation and Oversight via Code Execution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04725", "title": "Verb-ICL: Rethinking In-Context Learning for Structured Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04721", "title": "Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06971", "title": "AegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data Ecosystems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04699", "title": "Not Self-Decidable: LLMs Cannot Draw the Boundary of What an Agent Verifier Can Check", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04687", "title": "Understanding Errors in LLM-Based Question Answering over Imperfect Tables", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04683", "title": "Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06965", "title": "ACG-WAM: World-Action Modeling via Action-Conditioned Geometric Latent Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04681", "title": "RoboIRS: Inference-Time Internal Representation Steering for Generalist Robot Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04676", "title": "Extracting Persona Subspaces Through Iterative Nullspace Projection For Modulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06964", "title": "Principles that Guide, Actions that Inform: Agent Evolution via Knowledge Abstraction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06963", "title": "WavePrune: One period is often enough for RoPE", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04651", "title": "GS-Codec: A Gaussian-Splatting Bottleneck for Neural Audio Coding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04636", "title": "Does Neural Complexity Improve Health Misinformation Detection? A Leakage-Controlled Cross-Corpus Benchmark", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04631", "title": "The Numerical Linear Algebra of Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04620", "title": "Stance Drift: How AI-mediated Communication Distorts Our Message", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04616", "title": "PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04607", "title": "ForeAct3D: Policy-Grounded Future World Modeling for VLA Policies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04604", "title": "Anticipating the Consequences of Curriculum Decisions with Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04585", "title": "Frozen in a Frame: The Velocity Blind Spot in JEPA World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04580", "title": "Strong Helps Weak: Directional Cross-Modal Alignment Transfer in Multi-modal LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04569", "title": "From Transformers to Weighted Automata: Towards the Verification of Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04544", "title": "Label Agreement Does Not Measure Authorization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04541", "title": "Autonomous Structuring of Radiology Reports Across Modalities at Archive Scale Using an Open-Weight Large Language Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04537", "title": "PhaseGate: Phase-Aware CPU Retrieval Scheduling for On-Device LLMs on Unified Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04518", "title": "Length Generalization Needs Proper Regularization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04517", "title": "EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04512", "title": "Correctness Is a Direction: Geometric Answer Selection in Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04507", "title": "LoRA's Second Descent Extends Beyond Parameter Parity", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04506", "title": "EgoExo-Next:Benchmarking Vision-Language Models on Visual-Option Next-State and Cross-View Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04504", "title": "The Same Zero: Why Identical ASR Can Imply Different Guarantees in LLM-Agent Security", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04502", "title": "Localization Lens for Improving Medical Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06950", "title": "Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04499", "title": "Homogeneous Semantic Alignment and Hierarchical Expert Routing for Radiology Report Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04490", "title": "BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04489", "title": "DV-Lens: Revealing the Functional Organization of Language Model Parameters", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04467", "title": "Target-free Latent Safety Alignment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06949", "title": "AdaLoop: Adaptive-Depth Latent Reasoning for Audio Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04441", "title": "LocusRL: Diagnosing LLM Reward and Policy Interventions in Competitive Games", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04425", "title": "AgroGround: Multi-Granularity Grounded Recognition in Agriculture", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04424", "title": "On the Trade-off Between Information Loss and Generalization in Sparse Attention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04413", "title": "Specific Algorithmic Interpretability of Neural Networks: A Case Study on Textures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04412", "title": "Large Language Models and Augmented Democracy", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04409", "title": "Understanding and Mitigating Hallucination Escape in Tool-Using LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04403", "title": "Saying, Not Knowing: Aggressively GGUF-Quantized Small Language Models Still Write Rare Words They Can No Longer Define", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04401", "title": "Ideological Stance Detection in a Low-Resource Language: Polarization in Bangladeshi Public vs Private University Discourse on Social Media", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04399", "title": "GlitchPatch: Repairing Glitch Tokens in Frozen Language Models via Local Retokenization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04381", "title": "Beyond Plausibility: Verifiable Fine-Grained Image Editing on Structured Assets", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04370", "title": "Boundaries Agree, Labels Do Not: Intra-Annotator Dynamics as a Kind of Training Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04364", "title": "A Bird's-Eye View of Iterative Reward Design", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06940", "title": "Stabilizing language models under continual learning via condition-anchored distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04344", "title": "Hierarchical Credit Assignment for RLVR on Fused Gromov-Wasserstein Geometry", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04339", "title": "ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04333", "title": "Factorized Delayed Streams Modeling for LLM-based Streaming ASR", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04318", "title": "Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04303", "title": "What to Preserve in Recursive Computation: A Local Predictive Sufficiency Principle", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04286", "title": "CyTReX: Explainable AI-Based Cybersecurity Threat Reasoning Framework for DER Networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04278", "title": "Do RUL explanations hold up? Faithfulness and stability of attributions on C-MAPSS", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04269", "title": "Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04263", "title": "Multimodal Dual-Encoder Retrieval for Automated ICD Coding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04261", "title": "Playing social deduction games with reinforcement fine-tuned large language models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04255", "title": "Grounded in Time: A Multi-Source Dataset and Benchmark for Temporal Grounding in Robotic Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04239", "title": "Conformal Prediction with Paraphrase-Aware Scoring for LLM Uncertainty Quantification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04225", "title": "FlashGaze: Training-Free Multi-Scale Patch Pruning For Efficient Video Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06932", "title": "RADC: Risk-Aware Dual Caching for Vision-Language Test-Time Adaptation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04210", "title": "Can LLMs Separate Pasted Artifacts from User Speech? Absorption at Unmarked Prompt Seams", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04204", "title": "Clean: Second-order LLM Training at Linear Memory Cost via Nystr{ö}m Sketching", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04198", "title": "ALoDLM: Adaptively Looped Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04174", "title": "DimSteer: Steering LLM Authoring with Automatically Discovered Stylistic Controls", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04158", "title": "How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04156", "title": "Trajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04152", "title": "Kepler4D: Controllable Future Video Generation via 4D Scene State Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04140", "title": "ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04139", "title": "From Sight to Foresight: Predictive Spatial Reasoning in Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04138", "title": "Dual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04137", "title": "Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04134", "title": "Agentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04132", "title": "PB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04125", "title": "Representational Control over Self-Report & Behavior Coherence in LLM Risk-Taking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04118", "title": "LongSocialBench: Do Long-Context LLMs Understand Online Discussion Threads?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04104", "title": "Where Does the Semantic Gain Come From? A Reproduction and Extension of Semantic Knowledge-driven Contrastive Learning for Long-Tailed Recognition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04089", "title": "Pareto-Dominant Clarification: Post-Training Coding LLMs via PPO-Lagrangian Budget Constraints", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04047", "title": "Periscope: Extending Frozen Language Models Beyond Their Context Window", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04009", "title": "SUAVE: Unified Video-Action Models via Masked Diffusion", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04008", "title": "SkillScriptBench: Benchmarking Self-Evolution of Executable Agent Skill Packages Beyond Markdown", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04002", "title": "Do Language Models Need a Trainable Input Embedding Table? Fixed Minimal Token Codes at 1.7B-Class Scale", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03998", "title": "Behavioral History Outperforms Descriptions of the Person for LLM Synthetic Personas", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03972", "title": "Probabilistic Algorithms for Ising Machines from Optimization to Generative AI", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03962", "title": "BAIBAICHUCHU at the NTCIR-19 FinArg-3 Task: When Is Maximum Possible Profit Predictable from Investor Text?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03951", "title": "Evolving LLM-Generated Features for Interpretable Classification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03947", "title": "Synthesizing Physics Formulae with Transformers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03935", "title": "General Decision Models: Benchmarking and Insights Beyond Jev", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03896", "title": "AdaEva: Accelerating LLM-Driven Algorithm Design with Adaptive Partial Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03894", "title": "Proxy Confidence: Auditing Black-Box LLM Agents with a Surrogate's Log-Probabilities", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03872", "title": "Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03713", "title": "What Should World Models Forget? Stratified Retention for Continual Adaptation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03695", "title": "Language Models that Play Chess and Explain Their Moves", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03675", "title": "FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "frugalevo", "detail_path": "agent-research/2610.03675-frugalevo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03667", "title": "Planning to Learn", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03665", "title": "Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03632", "title": "World Embedding Benchmark", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03617", "title": "DEPICT: Scoring Text-to-Image Alignment by Answer Agreement", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03607", "title": "World Action Learning via Interaction-Centric Spectral Latent Guidance", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03587", "title": "AVL-JEPA: Preventing Causal Dynamics Information Collapse In Joint Embedding Predictive Architecture World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03585", "title": "Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03567", "title": "Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03551", "title": "Objects Without Morphisms: What LLMs for Mathematics Do Not Represent", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03531", "title": "Author Representation Strategies for Zero-Shot Authorship Attribution: A Comparative Study of LLM-Based and Embedding-Based Approaches", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03529", "title": "Divergence controls entropy in distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03525", "title": "Structured Composition of Verifiable Atomic Insights for Table-to-Report Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03524", "title": "From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03516", "title": "XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03502", "title": "Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03482", "title": "Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03480", "title": "Metropolis-Hastings Dominates Importance Resampling for Policy Composition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03468", "title": "A Vision-Language Model (VLM)-based Pipeline for End-to-End Procedural Modeling of Field-Grown Maize from Point Clouds", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03463", "title": "Generalization of Transformer-Based Neural Quantum States via In-Context Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03458", "title": "A Near-Zero Monitor Readout Is Not Evidence of Behavioral Control", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03448", "title": "Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03445", "title": "Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03432", "title": "OptiSelect: How does the Optimizer Shape Data Curriculum?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03421", "title": "CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03391", "title": "Native Action-Prior Learning from Videos for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03389", "title": "From Patching to Pruning Visual Computation in Vision Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03374", "title": "EVEWorld: Physical Evolution Supervision for Embodied World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03361", "title": "Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "follow-the-winners", "detail_path": "post-training/2610.03361-follow-the-winners/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03324", "title": "To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech Moderation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03296", "title": "JOVE: Joint Execution and Verification for Resource-Aware LLM Task Graphs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03289", "title": "Architecture-Dependent Fusion Pathways in MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03252", "title": "COSMI: COmpositional Synthesis of Multi-object Interactions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03240", "title": "Collective Bias Mitigation via Model Routing and Collaboration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03226", "title": "D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03223", "title": "AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "adastep", "detail_path": "agent-research/2610.03223-adastep/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03220", "title": "Evolving Hybrid Quantum-Classical Architectures for Image Classification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03215", "title": "StanceEval 2026: The Second Stance Detection Shared Task", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03834", "title": "LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03199", "title": "Predicting and Repairing Merge Collapse in Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03198", "title": "KV$^2$: A Self-Refining KV Cache", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03195", "title": "Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03193", "title": "Bridging Research and Practice: A Systematic Evaluation of Generalist and Dermatology-Specific Models in Clinical Skin Lesion Classification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03190", "title": "Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03187", "title": "Lightweight and Resource-Efficient Perception for Robotic Guide Dogs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03141", "title": "Behavior Pack Optimization for Video MLLM Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03136", "title": "Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03135", "title": "Page-EntroKV: Hardware-Aligned, Entropy-Weighted KV-Cache Eviction under Grouped-Query Attention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03124", "title": "The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03123", "title": "Foresight: planning future perception in streaming VLMs without retraining", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03112", "title": "Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM Signals", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03110", "title": "Ontological Instability and Statistical Amplification: The Paradox of \"Humanizing\" LLM-Generated Text", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03109", "title": "Emergent Structure in the Marginal Attention Space of Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03106", "title": "S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal Timescales", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03102", "title": "Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03098", "title": "Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03093", "title": "LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03084", "title": "NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03080", "title": "MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy Code", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03066", "title": "Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM Reranking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03063", "title": "HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03057", "title": "When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model Behavior", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03052", "title": "The Geometry of Knowledge Accessibility in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03039", "title": "HyperThink: Text-to-Parameter Hypernetworks for Efficient Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03036", "title": "WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live Websites", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03034", "title": "Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03027", "title": "Tailoring the Quantization Space for 1-Bit KV Cache Compression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03016", "title": "From Expression to Reaction: Role-aware Visual Transfer and Stimulus-guided Reasoning for Interlocutor Emotion Recognition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03002", "title": "Recursive Self-Improvement in Unified Multimodal Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02994", "title": "Sentry: Learning to Recover from LLM Agent Failures at Test Time", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "sentry", "detail_path": "agent-research/2610.02994-sentry/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02986", "title": "OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02974", "title": "From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02970", "title": "A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity Recognition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02957", "title": "Understanding Trajectory Heterogeneity in Federated World Model Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02953", "title": "SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02951", "title": "Dynamic Expert Pruning for Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02949", "title": "Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble Method", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14039", "title": "RAIN: Robotic Task Generalization with Region-Aware Interaction Networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02926", "title": "Output Language Confusion under Multilingual Prompt Contamination", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02910", "title": "Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLM", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02887", "title": "Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant Masking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02880", "title": "Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02878", "title": "Evaluating VQA in Vision Language Models using Cooperative Principles", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02877", "title": "Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging Difficulty", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02876", "title": "Seeing, Saying, but Not Using: From Reportable Spatial Facts to Usable States in Multimodal Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02873", "title": "ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone Evolution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02864", "title": "NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02856", "title": "Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02841", "title": "How Robust Is Multimodal Claim Verification to LLM Rewriting?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02840", "title": "PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02839", "title": "To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02835", "title": "All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02832", "title": "FastOPD: On-Policy Distillation for Lightweight VLA Deployment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02829", "title": "Clinical Concept Centers in LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02828", "title": "FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02819", "title": "Text-Centric Post-Training for Omni-Modal Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02817", "title": "RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02788", "title": "Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02775", "title": "Automatic Evaluation of Mental Health Stigma in Online Communication", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02772", "title": "Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge Editing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02755", "title": "FiberGeoText: A Vision-Language Model for Population- Level Organization of Superficial White Matter", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02754", "title": "Jumping up and down: Denoiser diffusion models for discrete ordinal data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02744", "title": "EpiWorld: Grounding LLM Policy Agents in Epidemiological World Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02718", "title": "Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02713", "title": "WakeKV: Reactive, Reversible KV Residency for Heads That Change Their Minds", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02702", "title": "Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original Premise", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02697", "title": "GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02695", "title": "Test-time Calibration Learning for Large Language Model Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02687", "title": "Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02684", "title": "Large language models exhibit unreliable updating of clinical judgment as patient evidence evolves", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02683", "title": "RAOA: Alternating-Operator Neural Computation with Programmable Radio Propagation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02673", "title": "Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02670", "title": "LEAP: Learning Efficient Action Proposals For LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02666", "title": "CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02665", "title": "Large Language Continuous Diffusion Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02659", "title": "Distributed Learning with Selective State Space Models: Architecture-Aware Convergence Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02657", "title": "Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02616", "title": "VERSE: Verified Self-Evolving Optimizer for Agent Harnesses", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02611", "title": "Scale-Recursive Rectified Flows for Few-Step Precipitation Ensembles", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02598", "title": "Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02597", "title": "GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02593", "title": "Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02574", "title": "DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10563", "title": "SLVR: Structured Latent Visual Reasoning via Human-like Reasoning Flows", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02549", "title": "Evaluating Multi-Dimensional Generalization of Large Language Models in Temporal Extraction Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02521", "title": "Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02516", "title": "Student-Guided Teacher Distillation for Efficient LLM Task Routing: Positioning Against Jev-Style System-1 Classifiers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02513", "title": "From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02508", "title": "World Action Modeling with Progressive Visual Planning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02507", "title": "MeshQuery: Agentic Seam Planning for UV Parametrization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02497", "title": "LiteEMG-FM: An Efficient and Deployable Foundation Model for Robust EMG Sensing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02492", "title": "Right Order, Wrong Scale: Auditing LLM Judges for Occupational AI Measurement", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02488", "title": "Harnessing LLMs as Agents: What Does It Cost?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02472", "title": "APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02462", "title": "Capability Scaling-Down Laws for LLM Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02460", "title": "CUEing User Simulators: Calibrated User Embeddings for Multi-Turn Benchmarking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02455", "title": "FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02451", "title": "A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02442", "title": "AI-driven Thermal-aware Data Center Capacity Planning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02438", "title": "Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02432", "title": "Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02425", "title": "Finding the Move Is Not Winning the Game: XiangqiBench for Closed-Loop Evaluation of LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02413", "title": "Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02404", "title": "Trained Agentic Context Management", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02398", "title": "Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02388", "title": "Octrees as an Explicit 3D Language", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02386", "title": "Social bot detection in the age of ChatGPT: Challenges and opportunities", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02381", "title": "Latent-MOPD: Latent Multi-Teacher On-Policy Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02375", "title": "EviDent-CBCT: Evidence-Bottlenecked Report Generation from Dental CBCT under Non-Exhaustive Report Supervision", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02368", "title": "Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02361", "title": "SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02355", "title": "Why Does Adaptive Batching Help LLM Pretraining? A Perspective from Unbounded Variance", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02351", "title": "DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02344", "title": "Drive vs. Decay: On the Training Dynamics of Joint-Embedding Predictive Architectures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02323", "title": "World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02320", "title": "DeskForge: Dense Supervision from Desktop Environments for Computer-Use Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02206", "title": "KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02199", "title": "TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "taco-optimizer", "detail_path": "foundation-models/2610.02199-taco-optimizer/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/taco-optimizer-a100-20261002.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.02196", "title": "InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02193", "title": "Hierarchical Continuous Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02191", "title": "The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02190", "title": "Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02181", "title": "OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02302", "title": "Intent-Hiding Jailbreaks: An Information-Theoretic Framework for Compositional Attacks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02163", "title": "AutoCompact: Learning When to Compact Context in Long-Horizon Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "autocompact", "detail_path": "agent-research/2610.02163-autocompact/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02298", "title": "EditHero: A Benchmark for Long-Horizon Part-Level 3D Editing and Vibe Modeling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02150", "title": "From Knowledge Access to Source Learning: Developing Source-Specific Competence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02148", "title": "Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "omni-embed-mini", "detail_path": "foundation-models/2610.02148-omni-embed-mini/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02144", "title": "Faynt: Scaling and Optimizing Policies for Competitive Melee", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02142", "title": "Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02128", "title": "Sample complexity bounds for categorical Markov random fields via Discrete Diffusions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02126", "title": "Local Support Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02120", "title": "SkeleWAM: Skeleton World-Action Modeling for Efficient Robotic Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02117", "title": "Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "where-opd", "detail_path": "post-training/2610.02117-where-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02092", "title": "Scalable, Transferable Meta-network for Data Selection Requires a Different Loss (and Why the Obvious Choice is Problematic)", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "tess", "detail_path": "foundation-models/2610.02092-tess/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02091", "title": "GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02076", "title": "LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "llm2jev", "detail_path": "foundation-models/2610.02076-llm2jev/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02054", "title": "UniWAM: Unified World-Action Model", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02045", "title": "Form and Void: Entangled Composition through an Autonomous AI Agent", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02039", "title": "CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "carm", "detail_path": "post-training/2610.02039-carm/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02022", "title": "Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02021", "title": "Task-Adaptive Grounded 3D-Programmers Using 2D VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02019", "title": "Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02015", "title": "On Language Drift during RLVR Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02002", "title": "Mem++: Non-Destructive Memory for Long-Term Organizational LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "mem-plus-plus", "detail_path": "agent-research/2610.02002-mem-plus-plus/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01999", "title": "From Reasoning Failures to Composable Video Spatial Intelligence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01984", "title": "Universal Byte-Level Encoding: UTF-8/UTF-16 Routing to Reduce Cross-Script Token-Budget Disparities", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01981", "title": "Universal interpolation for deep residual self-attention networks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01973", "title": "Token-Level Video Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "tvrl", "detail_path": "post-training/2610.01973-tvrl/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01967", "title": "FastCI: Efficient GPU-Intensive CI for LLM Training Frameworks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01963", "title": "Counterfactual Auditing of Bias in Open-Source Large Language Models for Clinical Triage", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01962", "title": "SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01947", "title": "Latent JEPA: Abstract Future Prediction for Latent Reasoning in Chemistry", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01944", "title": "Anti-Persona: Disrupting Unauthorized Identity Binding and Recognition in Personalized Vision--Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01939", "title": "Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01938", "title": "A rubric landscape for evaluating clinical reasoning in large language models: what exists, what is missing, and what needs to be combined", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01934", "title": "Learning to Predict Distributions over Weight Updates for Test-Time Adaptation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01921", "title": "Cross-Lingual Alignment for Decoder-Only Models using MoE Routers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01917", "title": "MoLE: Mixture of Latent Experts for Complementary Visual Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01896", "title": "Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "gmc-grpo", "detail_path": "post-training/2610.01896-gmc-grpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01889", "title": "Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01887", "title": "TRACE: Tackling Real-World Resource Assignment Problems via Agentic Heuristic Design", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01873", "title": "Where LLMs Fail with Visualization DSLs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01847", "title": "Detecting Inconsistencies in Model Specifications with LLM-as-Verifier Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01846", "title": "Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01835", "title": "Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01821", "title": "Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01815", "title": "Debias Anything: Fairness with Diversity without Supervision in Diffusion Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01794", "title": "Continuous Conditioning of VLAs with Augmenting EMG and Visual Task Descriptors", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01785", "title": "VETO: Video Efficient Token Optimization for Vision Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "veto", "detail_path": "foundation-models/2610.01785-veto/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/veto-a100-20261002.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.01768", "title": "The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web Fetching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01767", "title": "A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01766", "title": "VideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01754", "title": "Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01741", "title": "ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02284", "title": "Effects of interpulse-interval variation on deep-learning classification of bat vocalizations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01710", "title": "CoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01698", "title": "ActiveWAM: Evidence-Aware Active Vision for World-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01696", "title": "Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01687", "title": "Architectural Sampling: Test-Time Scaling via Computational Diversity in Frozen Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01670", "title": "Do MLLM Judges Judge the Edit? Auditing Bias in Image Editing Evaluation with Verified Quality Preservation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01652", "title": "Iterative Policy Refinement through Semantic Rollout Analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01649", "title": "CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01640", "title": "Not All Error Yields to Scale: Where Scaling Stops in Vision-Language Inference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01637", "title": "Fusing Visual and Textual Representations via Multi-layer Fusing Transformers for Vietnamese Visual Question Answering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01634", "title": "Yo-ByT5: Efficient and High-Fidelity Diacritic Restoration for Yorùbá", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01627", "title": "What Makes Something Hard(er)? Explaining Question Difficulty in Natural Language", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01625", "title": "Beyond Domain-Level Adaptation: Margin-Oriented Semantic-Appearance Interaction Correction for Personalized Federated Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01616", "title": "Can LLMs Reliably Annotate Bioassay Metadata to Improve Data Readiness?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01605", "title": "Hob-VL: A Benchmark for Visually Grounded Boolean Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01595", "title": "Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01592", "title": "Which LLM to pick? Online Active Model Selection for Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01578", "title": "The hidden advantage of mask resampling: a theory of masked autoencoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01569", "title": "Managing Context and Communication in Distributed Agentic UAV Swarms", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01559", "title": "Completion Aware Guidance for World Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01548", "title": "Range-GRPO: Policy Optimization via Pairwise Relations among Reward Intervals", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "range-grpo", "detail_path": "post-training/2610.01548-range-grpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01537", "title": "FedFit: Federated Fine-Tuning of LLMs via Vector-Bank Parameterization and Quantization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01531", "title": "Towards Reliable Vision-Language Models for Autonomous Driving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01530", "title": "Calibrating Prediction Timeliness Through Multi-Objective Hyperparameter Optimization for Remaining Useful Life Prediction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01519", "title": "Auto-Formalizing Neuro-Symbolic Predictors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01514", "title": "How the Audit Rule Shapes Faithful Factor Explanations in LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01513", "title": "Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01509", "title": "Sharpening Tax in Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "sharpening-tax", "detail_path": "post-training/2610.01509-sharpening-tax/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01508", "title": "OverAct: Measuring and Mitigating Proactive Over-Authorization in LLM Tool-Calling Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01499", "title": "VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01497", "title": "OpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01496", "title": "SALD: Self-Referenced Advantage Learning for Diffusion Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01492", "title": "Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01490", "title": "The Persona Is Still There, but Who Is Speaking? Latent Identity Reversion in Persistent AI Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01471", "title": "When Does a Second Model Help? Cross-Model Review in LLM Verification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01434", "title": "MWOP: Modality-aware Width-wise Operation Pruning for Efficient MLLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "mwop", "detail_path": "foundation-models/2610.01434-mwop/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01428", "title": "Generalization Is Stability, Not Accuracy: Multi-Axis Evaluation of LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01395", "title": "AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "af-muon", "detail_path": "foundation-models/2610.01395-af-muon/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01393", "title": "LLM-Assisted Discovery of Typed Semantic Links for Ontology Network Construction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01389", "title": "AiSearch: Interactive Multi-Modal Search with VLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01345", "title": "ARCCS: An Automated Regulatory Compliance Checking System", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01324", "title": "Evaluating Biomedical Reranking for LLM-Based Question Answering over Longitudinal Clinical Notes", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02274", "title": "Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01286", "title": "Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01275", "title": "Know When to Hold 'em: Correct-Token Retention in Uniform-State Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01257", "title": "Science Utopia? Closed-Loop LLM Simulation of Academic Research Ecosystems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01243", "title": "When the Judge Acts: Auditing VLM-Guided Image Selection on Culturally Situated Prompts", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01241", "title": "Evaluating the Robustness of Japanese LLMs to IME-Related and Typographical Errors", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01234", "title": "ASCRIBE: Atomic and Significance-Based Reasoning for Thai Clinical SOAP Note Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01223", "title": "Have an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01218", "title": "AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01192", "title": "FlashBack: Knowing When to Remember in Streaming Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01184", "title": "ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01180", "title": "Skeleton-and-Strategy Prompting: Training-Free Negation Understanding for Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01177", "title": "Temporally-Resolved Token Attribution Reveals the Generation Dynamics of Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01172", "title": "Learning Rate Transfer for Hybrid Transformer-SSM Architectures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01168", "title": "Detect, Explain, Interpret: An End-to-End Benchmark for Time Series Anomaly Detection, Explainability and Interpretability", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01166", "title": "CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01153", "title": "Looping Beyond Twice: A Scalable Recipe for Looped Mixture-of-Experts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02270", "title": "Reliability Stress Tests and Decision-Time Routing for Chest X-ray Vision-Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01127", "title": "Counting and Min-Cost Encoding for Tokenization in Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01118", "title": "Madeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02267", "title": "Fast Models, Slow Evidence: A Paired and Self-Audited Evaluation of System-1 Decision Models for LLM Agent Harnesses", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03799", "title": "StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01076", "title": "GLoC-EHR: Evidence-Cited Clinical Reasoning over Global Context and Local EHR Events", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01066", "title": "Probe with Participation Trophies: Random-Reward RL as a Probe of LLM Capability", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01062", "title": "Kernelized Activation Steering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01054", "title": "Capturing In-Context Learning Dynamics with Task Operators", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01046", "title": "Sentence Specificity Scores for Collaborative Technical Documentation: A Domain-Transfer Study", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01042", "title": "Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03797", "title": "WAMJET: A Harness for World Action Model Acceleration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01037", "title": "SLIM: Simplex-Lattice Interpolation Merging", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01027", "title": "LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01026", "title": "It Takes Workflows to Evolve Better Workflows", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "flowright", "detail_path": "agent-research/2610.01026-flowright/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01017", "title": "Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01016", "title": "Scaling and Distilling Text Embeddings for Better Diffusibility", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00983", "title": "The Devil Is in the Reconstruction Loss Scale: Rethinking Optimization in LLM Quantization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00981", "title": "NarrativeFlow: Flow-Based Vision-Language-Action Model Using Robot Velocity Fields", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00976", "title": "Variational Streaming Flow: Probabilistic Forecasting in Physical Time", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00973", "title": "Concept Driven Domain Adaptation: Finding an Abstract Needle in a Haystack", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00969", "title": "A Citation-Grounded Benchmark for Trustworthy Earnings Call Transcript Analysis with Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00964", "title": "RPTune: Learned Context Curation for LLM Catalog Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "recommendation", "key": "rptune", "detail_path": "reproductions/2610.00964-rptune/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00958", "title": "Role-aware Heuristic Episodic Attention for Conversational LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "rea", "detail_path": "foundation-models/2610.00958-rea/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00954", "title": "Beyond Leaderboards: Tokenomics of Agentic Small Language Model Ensembles", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00952", "title": "A Matched-Budget Audit Framework for Recaptioned Image-Text Supervision Distributions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00922", "title": "EyeTAG: Eye Trajectory-Aware Gaze Estimation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00910", "title": "The Geometry of Contextual Relations: Language Models Address Facts by Order of Mention", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00906", "title": "ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "active-saddler", "detail_path": "agent-research/2610.00906-active-saddler/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00903", "title": "Sharpen Before You Adapt: Data-Free Entry-State Sharpening for Test-Time Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00899", "title": "TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00898", "title": "When Do Biological Reasoning Models Use Their Biological Inputs?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00894", "title": "Clock Diffusion: Efficient Semi-Autoregressive Continuous Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00883", "title": "DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00881", "title": "Machine Translation for Sign Languages", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00878", "title": "UniTrackPLA: Unified Panorama-Language-Action Model for Instruction-Guided Navigation and Dynamic Person Tracking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00864", "title": "Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00859", "title": "CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00855", "title": "Lang3DSeg: Annotation-Free Open-Vocabulary 3D Segmentation with Point Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00848", "title": "Geometric Similarity in VLM Low-Level Vision Representations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00840", "title": "Contextual trajectory and incremental contextual displacement: Towards using LLMs to understand dynamic, utterance-specific meaning construction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00838", "title": "SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "sharpo", "detail_path": "post-training/2610.00838-sharpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00833", "title": "VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00827", "title": "Verbalized and Internal Probabilities Are Coupled in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00825", "title": "Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06903", "title": "Component and Dimension Sparsity in Transformer Refusal Mechanisms", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00814", "title": "Training-Aware Target Coverage for Synthetic Data Selection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14029", "title": "Can We Trust This Evaluation? Instance-Level Reliability of LLM-as-a-Judge", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00809", "title": "Paying for Too Many Tokens? Valid and Cost-Efficient Multimodal LLM Annotation with Simple Heuristics", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00795", "title": "Can large language models unlock discrete data in ophthalmic diagnostic reports?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00779", "title": "Effective Synthetic Data Curation Requires Group-Level Signals", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03792", "title": "What Do Verifiable Rewards Teach Video-Language Models About Time? A Controlled Multi-Model Study", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00727", "title": "CF-JEPA: Improving Robustness of JEPA World Models via Controllability Factorization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00722", "title": "JEPA-TTT: Persistent Test-Time Training of Latent World Models for Planning under Dynamics Shifts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00717", "title": "Sequential Functional Structured Tucker Compression for Large Language Model Attentions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00707", "title": "Initialization Improves LLM-Driven Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00704", "title": "SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00694", "title": "How Divergence Becomes Decision Flips in Compressed Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00689", "title": "Towards Robust Numerical Claim Verification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00687", "title": "Leto: Fast In-Place Recovery for LLM Training on Surviving Hardware", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00685", "title": "Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00682", "title": "Ontology-Grounded, Reasoner-Verified Benchmarks for Evaluating LLM Reasoning in Scientific AI", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00680", "title": "Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00677", "title": "Harnessing Vision-Language Models for Perceptual Quality Assessment and Autonomous Content Adjustment in Augmented Reality", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00675", "title": "LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00673", "title": "Closing the Loop: Practical Training Recipes for Looped Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00666", "title": "VisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00665", "title": "Analysis of Quantized and Efficiently Adapted Protein Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00663", "title": "Backdoor Containment via Expert Quarantine and Shutdown in LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00661", "title": "Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00656", "title": "Lingtai: What Concept Geometry Reveals--and Does Not Reveal--About LLM Inference", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00651", "title": "Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00650", "title": "Self-Evolving Coding Rules for AI Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "rule-evolve", "detail_path": "agent-research/2610.00650-rule-evolve/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00647", "title": "Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00638", "title": "TacDyn-WAM: Learning Implicit Tactile Dynamics in a Heterogeneous Visuo-Tactile World Action Model", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00636", "title": "CompMat-Bench: Benchmarking AI Agents for Computational Materials Science", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00623", "title": "HAWK: Rethinking Multimodal Drafting for Speculative Decoding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "hawk", "detail_path": "foundation-models/2610.00623-hawk/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02254", "title": "Overcoming Challenges of Interpretive Structural Modeling with Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00609", "title": "Legal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00604", "title": "MIKASA-Robo-VLA: Benchmarking Memory in VLA Models for Long-Horizon Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00592", "title": "ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00573", "title": "FORTE: Adaptive Scoring and Exact Keyframe Selection for Long-Video Question Answering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00569", "title": "Scaling Collider Event Generation with Residual-Quantized Tokens", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00568", "title": "Emergent Unfaithfulness: How Alignment Training Causes Language Models to Silently Override Task Faithfulness", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00562", "title": "Can LLMs Reason Over Long Horizons? An Empirical Evaluation of Context Strategies for Longitudinal Clinical Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00559", "title": "PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00541", "title": "Random Recursive Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00499", "title": "Denoising Surface: Modeling and Predicting Inference Cost for Diffusion LLM Serving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14028", "title": "Pick the Mixture, Not the Samples: Combinatorial Data Selection for LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00497", "title": "Gumbel Straight Flow: Distilling Autoregressive Models into One-step Flow Maps", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00487", "title": "ScaffoldM3C: A Multimodal Sequential Monte Carlo Framework for Generative Stable Construction Planning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00465", "title": "AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00436", "title": "Every Batch Is Its Own Validation Set: Leave-One-Out Gradient Matching for Online Data Selection in LLM Fine-Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00432", "title": "XOR-Trellis: Ultra-Low-Complexity Dequantization and Curvature-Aware Hadamard-Free LLM Quantization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02247", "title": "Toward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00431", "title": "ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00426", "title": "IrekoGPT: Turning Structured Pruning into Post-Hoc Slimmable LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "foundation-models", "key": "irekogpt", "detail_path": "foundation-models/2610.00426-irekogpt/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00416", "title": "Benchmarking Prompt Optimization of Large Language Models With Chess", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00406", "title": "LLM-as-a-Judge for Low-Resource Languages: Adapting Ragas and Comparative Ranking for Romanian", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00400", "title": "Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00399", "title": "Metacognitive Reasoning in Energy Based Models using Instance Based Learning Theory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00398", "title": "WIPSNet: Deep Learning for Paediatric Wheeze Detection from Overnight Impedance Pneumography", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00388", "title": "T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "t2spo", "detail_path": "post-training/2610.00388-t2spo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2609.39304", "title": "Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06902", "title": "Tree Navigation Without LLM Summaries: A Matched-Cost Study of Hierarchical Retrieval for Long-Document QA", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00374", "title": "Faithful Chart Generation for Multimodal Deep Research: Frame-Evidence Co-Adaptation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00363", "title": "Deep Learning for Anomaly Detection in Railway Systems: A Structured Survey", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08840", "title": "Beyond the Sycophancy Score: How Task, Model, and Pressure Shape LLM Yielding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.33973", "title": "FINGR: Learning Dexterous Hand Control for Real-World Rubik's Cube Solving", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.33551", "title": "FoLD: Force-Informed Learning for Dexterous Articulated Object Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.28312", "title": "VGM-VS: Rethinking Visual Geometry Model for High-Precision Visual Servoing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.23961", "title": "Colon3R: Cross-Domain 3D Reconstruction from Monocular Colonoscopic Video", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2609.11326", "title": "Rice's Theorem under Self-Modification: Elevation Operators and a Normal Form", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2608.24101", "title": "TrAct: Bridging Robot Control and Visual Prediction with Visual Tracks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.29237", "title": "CorrelationFlow: A Training-Free Geometric Approach for LiDAR Scene Flow Estimation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.23473", "title": "PRISM: Polynomial Representations for Interaction-Structured Motor Control", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2607.07968", "title": "Soft Robotic Exogloves for Dexterous Mobility -- Towards Personalized Rehabilitation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.24472", "title": "G$^3$VLA: Geometric Inductive Bias for Vision-Language-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.22631", "title": "4DVLT: Dynamic Scene Understanding with Worldline-Centered Vision-Language Tracking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.17029", "title": "DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.16710", "title": "Misinformation Propagation in Benign Multi-Agent Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.16569", "title": "PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.16203", "title": "DynFS-MoE: Dynamic Functional-Structural Mixture-of-Experts for Post-Traumatic Epilepsy Diagnosis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.13497", "title": "SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.13349", "title": "ProReviewer: Evidence-Driven Investigation for Scientific Peer Review", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.12402", "title": "DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.12306", "title": "UGV-Conditioned Multi-UAV Informative Planning on a Shared Exposure Belief", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.11152", "title": "P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.10288", "title": "MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.06788", "title": "Explain Like I'm 5 or Whatever I Choose: Evaluating the Potential for Interactive Complexity in Language Model Responses", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.06177", "title": "Ouvia: A User-centered Framework for Measuring Usability of Speech Translation in Real-World Communication Scenarios", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.04457", "title": "Imagine Before You Draw: Visual Prompt Engineering for Image Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.04149", "title": "CoPark: Learning Reactive Parking via Self-Play", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.03177", "title": "ConTrack: Constrained Hand Motion Tracking with Adaptive Trade-off Control", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.02994", "title": "Learning Reusable Agent Subroutines from Experience", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.01458", "title": "LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.00981", "title": "Robust Asynchronous Planning via Auto-Formalization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.00374", "title": "Constrained Whole-Body Tracking for Humanoid Robots", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.29858", "title": "Masked Diffusion Vision-Language Models for Temporal Action Localization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.29054", "title": "T2J-BENCH: Benchmarking Coding Agents on Execution-Grounded PyTorch-to-JAX Repository Migration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.28093", "title": "ConRAG: Consensus-Driven Evidence Flow for Multi-Hop Question Answering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.20364", "title": "When Reasoning Supervision Hurts: TTCW-Based Long-Form Literary Review Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.20337", "title": "Capability $\\neq$ Interpretability: Human Interpretability of Vision Foundation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.18041", "title": "OmniSelect: Dynamic Modality-Aware Token Compression for Efficient Omni-modal Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.14315", "title": "TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.20223", "title": "Why Latent Actions Fail, and How to Prevent It", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.11840", "title": "Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.10659", "title": "When Can Digital Personas Reliably Approximate Human Survey Findings?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.08434", "title": "Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.27193", "title": "Real-Time GPU-Accelerated Monte Carlo Evaluation of Safety-Critical AEB Systems Under Uncertainty", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.00915", "title": "Learning Dynamic Evidence Routes for Vision Transformer Probing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.23069", "title": "ContextWeaver: Selective and Dependency-Structured Memory Construction for LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.18360", "title": "Omni-Embed-Audio: Leveraging Multimodal LLMs for Robust Audio-Text Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.17886", "title": "Latent Preference Modeling for Multi-Session Personalized Tool Calling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.13993", "title": "Reward Design for Physical Reasoning in Vision-Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.12128", "title": "Phantom Paradoxes: Language Models Treat Unresolved Circular Truth Dependence as Contradiction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.11390", "title": "Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.05656", "title": "SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.03925", "title": "AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian Computation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.03414", "title": "KiToke: Distribution-Aware Token Compression for Video Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.02408", "title": "F2F-AP: Flow-to-Future Asynchronous Policy for Real-time Dynamic Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.01567", "title": "MobiGuide: Vocabulary-Guided Online Recovery for Mobile Manipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.25923", "title": "On Challenges in Evaluation Methodology: A Review", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.00073", "title": "Terminal Agents Suffice for Enterprise Automation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.26783", "title": "Can We Change \"Stroke Size\" to Simplify Regression Learning?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.23678", "title": "PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.19714", "title": "LoopRPT: Reinforcement Pre-Training for Looped Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.16557", "title": "BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.14371", "title": "OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.13509", "title": "Verification and Forward Invariance of Control Barrier Functions for Differential-Algebraic Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.12468", "title": "Selective Prediction Forgetting for Adaptation of Weakly Supervised Localization of Histology Images", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.08491", "title": "Global Cross-Modal Geo-Localization: A Million-Scale Dataset and a Physical Consistency Learning Framework", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.07815", "title": "HybridStitch: Token-Adaptive Model Stitching for Efficient Diffusion Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.01502", "title": "Geometric Alignment without Functional Equivalence: A Layer-wise Analysis of the Speech-Text Modality Gap", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.00578", "title": "Draft-Thinking: Learning Efficient Reasoning in Long Chain-of-Thought LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.16705", "title": "HERO: Learning Humanoid End-Effector Control for Visual Whole-Body Open-Vocabulary Object Grasping", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.12881", "title": "Semantic Communities and Boundary-Spanning Lyrics in K-pop: A Graph-Based Unsupervised Analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.12244", "title": "TGPO: Trace-Guided Policy Optimization for Robot Task Planning via Verifiable Subgoal Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.07549", "title": "When Is Enough Not Enough? Illusory Completion in Search Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.05359", "title": "Multimodal Latent Reasoning via Hierarchical Visual Cues Injection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.02326", "title": "Language Steering for Multilingual In-Context Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.22050", "title": "MasalBench: A Benchmark for Contextual and Cross-Cultural Understanding of Persian Proverbs in LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.20776", "title": "Learning From a Steady Hand: A Weakly Supervised Agent for Robot Assistance under Microscopy", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.10085", "title": "CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamics", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.08689", "title": "QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.08010", "title": "CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.04948", "title": "SKATER: Synthesized Kinematics for Advanced Traversing Efficiency on a Humanoid Robot via Roller Skate Swizzles", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.23044", "title": "Video-Browser: Towards Open-web Agentic Video Browsing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.21201", "title": "Schrödinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.13399", "title": "Dual-Evolving Reinforcement Learning for Automated Reward Design", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2512.01495", "title": "ELVIS: Enhance Low-Light for Video Instance Segmentation in the Dark", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.17735", "title": "Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.09568", "title": "VEDA: Generation of 3D Molecules via Variance-Exploding Diffusion with Annealing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.00110", "title": "Chain of Time: In-Context Physical Simulation with Image Generation Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.23160", "title": "Reclaiming Low-Quality Instruction Data with Rule-Guided LLM Reconstruction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.13928", "title": "LLMs Can Get \"Brain Rot\": A Pilot Study on Twitter/X", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.12306", "title": "A large-scale pipeline for LLM-assisted corpus annotation: variation and change in the English consider construction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.07231", "title": "EconCausal: A Context-Aware Economic Reasoning Benchmark for Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2509.21193", "title": "Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2509.18369", "title": "Align Where the Words Look: Cross-Attention-Guided Patch Alignment with Contrastive and Transport Regularization for Bengali Captioning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2509.09658", "title": "Measuring Epistemic Humility in Multimodal Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2508.06149", "title": "Scaling Personality Control in LLMs with Big Five Scaler Prompts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2508.03829", "title": "Majority Bit-Aware Watermarking For Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2507.12553", "title": "Is This Just Fantasy? Language Model Representations Reflect Human Judgments of Event Plausibility", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2507.04949", "title": "Monte Carlo Tree Search with Tensor Factorization for Optimization Problems in Robotics", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2506.20642", "title": "$π$-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2506.04713", "title": "Enabling Validation for Robust Few-Shot Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2505.21710", "title": "Assessing and Refining ChatGPT's Performance in Identifying Targeting and Inappropriate Language: A Comparative Study", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2505.13546", "title": "Prompt Stability Matters: Evaluating and Optimizing Auto-Generated Prompt in General-Purpose Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2505.03380", "title": "Synergistic Vision-Language Reinforcement Enables Scalable On-Demand Analysis across Diverse Clinical Tasks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2502.12713", "title": "Uncertainty Propagation for Echocardiography Clinical Metric Estimation via Contour Sampling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2502.10570", "title": "Quantifying the Impact of Motion on 2D Gaze Estimation in Real-World Mobile Interactions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2501.12375", "title": "Video Depth Anything: Consistent Depth Estimation for Super-Long Videos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2412.12877", "title": "PRIMEdit: Probability Redistribution for Instance-Aware Multi-Object Video Editing With a New Benchmark Dataset", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2412.12048", "title": "A LoRA is Worth a Thousand Pictures", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00348", "title": "Removing the NEEDLE in the Haystack: Backdoor Removal in LLMs via Weight Orthogonalisation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14025", "title": "Contrastive Covariance Subspaces for Activation Steering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14024", "title": "Beyond a Better Score: Long-Horizon Agentic ML Development and Evaluation Protocol for Physics Time Series", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00333", "title": "LEGO-OPD: Factorized Teacher Composition for Multimodal On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "lego-opd", "detail_path": "post-training/2610.00333-lego-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00332", "title": "The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "weakest-link", "detail_path": "post-training/2610.00332-weakest-link/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.08835", "title": "Leveraging LLM-Generated Explanations for Detecting Emotionally Rewritten Fake News", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14018", "title": "RoboHarness: A Simple Harness Outperforms VLA and World Actions Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02241", "title": "Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00320", "title": "Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03769", "title": "Bayes-Sufficient Compression Is Not Enough: How Does Communication Help Multi-Agent Systems?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00317", "title": "DriftOPD: Sequence-Level Reverse-KL Distillation for One-Step VLA Policies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "drift-opd", "detail_path": "post-training/2610.00317-drift-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00316", "title": "DuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14009", "title": "When Log Parsing Removes What Matters: Detecting Failures in Distributed GPU Workloads", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00309", "title": "Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06896", "title": "Medical Image Alignment Assessment as a Test of Generalist Visual Reasoning in Frontier Multimodal Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14006", "title": "Coding LLMs Can Be Harnessed to Learn Interpretable Models from Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08833", "title": "CoDR: Training-Free Confidence-Drift Remasking for Diffusion Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00302", "title": "Decoding the Disaster: Multi-Task Geospatial Reasoning with Vision-Language Models and Crowdsourced Imagery for Disaster Mapping", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14005", "title": "Artificiality's First Exam: An LLM-Referenced C-test for Supraintelligence", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08830", "title": "MoR-MLLM: Mixture of Recursions for Efficient Multimodal Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14000", "title": "VH-GPO: Verified Handoff for LLM Agent Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13999", "title": "SemTree: Judge-Aware Semantic Decision Trees for Inspectable and Repairable Rule Decisions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08829", "title": "Emo-Jev: Probabilistic Reasoning for Emotion Classification with Jev", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03759", "title": "BridgeCast: Bridging Ocean Wave Forecasts to Reanalysis via Flow Matching with Exogenous Variables", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13995", "title": "GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12495", "title": "Kairos: Toward a Byte-Level Foundation Model for Every Modality", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00296", "title": "Certainty Is Not Just Correctness: Rethinking Token-Level Certainty in LLM Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10552", "title": "Freeze the Decoder, Heal the Encoder: Parameter-Efficient Adaptation for SVD-Based KV-Cache Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12494", "title": "Algebraic Integer Quantization for Machine Learning Applications", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08822", "title": "A Vehicle-Integrated Approach to Digital Twin Deployment for Bridges Through Drive-By Sensing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10550", "title": "Diffu-LoRA: A Novel Low-Rank Adaptation for Personalized Diffusion Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00268", "title": "MOVE: Multimodal Open-world Verification and Expansion for Graph Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08818", "title": "Just for FUNS: LLM-Guided Spatio-Temporal Graph Node Generation for Forecasting Unobserved Node States", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06889", "title": "Zero-Shot Visualization: Exploring Text Corpora with User-Prompted Axes", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08813", "title": "Pre-training, Reasoning, Benchmarking: X-ray Report Generation on CheXpert Plus Dataset", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13982", "title": "PRIME: Frequency-Aware Unified Pruning and Merging for MoE Compression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08811", "title": "KVFetch: Temporal Prefetching for the Missing Half of KV Cache Compression", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03741", "title": "Logit-Aware MIMO AirComp for Distributed Mixture-of-Experts LLM Inference over Wireless Edge Networks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00223", "title": "A Holistic Assessment of the Carbon Footprint of Noor, a Very Large Arabic Language Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00204", "title": "Query Independent Variable Rate Visual Token Coding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00196", "title": "GPEC: Efficient Pre-LLM Gaussian Process Embedding Correction for Cardiac Video Caption Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00106", "title": "SyntheticHLS: Building Diverse Synthetic High-Level Synthesis Datasets using LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00097", "title": "DramaAgent: Agentic Storytelling Video Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00069", "title": "A Framework for Egocentric and Exocentric Procedural Understanding via Temporal Segmentation and Semantic Abstraction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00040", "title": "DSSR-3D: Decoupled Reasoning for View-Dependent Referring in 3D Gaussians", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00031", "title": "Seeing the City or Recognizing the Place? What Street-View Imagery Adds Beyond Existing Urban Data in VLM-Based Urban Sensing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00024", "title": "Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13956", "title": "MDN-VJEPA: Multimodal Probabilistic Joint-Embedding World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12474", "title": "TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00003", "title": "STATERA: Hidden Mass Estimation via Zero-Shot Sim-to-Real Kinematics using Frozen Temporal Tubelets", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00092", "title": "BudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00087", "title": "Legal text classification in Korean sexual offense cases: from traditional machine learning to large language models with XAI insights", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00083", "title": "\"very likely\" Means \"uncertain\"? How LLMs Diverge from Humans in Linguistic Uncertainty Quantification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00070", "title": "Measuring Human-Like Bias in LLMs? A Critique of Human-Derived Bias Constructs in LLM Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02214", "title": "MiDShip: Multimodal Dataset of Ship Cargo Hold Structures for Engineering Design", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00049", "title": "Fast Polynomial Transcendentals for LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00025", "title": "Measuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13959", "title": "LACRM: LLM-Guided Mining of Directed Advertiser Competition Relationships in E-Commerce Advertising", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00007", "title": "On-Device Named-Entity Recognition: A Deployability Study of Accuracy, Cost, Reliability, and Confidence", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06861", "title": "When Does External Guidance Help LLM Reasoning? A Bias-Variance Theory of Guidance-Augmented GRPO", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20334", "title": "TreeFlex: Agents Navigating Their Own Search Trees", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20253", "title": "Repairing Speech Access After Text Updates with Frozen Affine Fields", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19796", "title": "Learning Perception to Action Rules through Reinforcement Learning for Theory-of-Mind Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19476", "title": "What Does LALM Post-training Learn? Rethinking Audio Understanding and Reasoning Capabilities", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18853", "title": "Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18766", "title": "Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18755", "title": "PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18738", "title": "Enabling Token-wise Importance Sampling in Off-Policy RLVR with Proximal KL Regularization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18695", "title": "A Refresh Interval Does Not Fully Specify a Refresh Schedule: Learning-Rate-Dependent Placement in Kronecker-Preconditioned Language Model Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18613", "title": "Does self-distillation improve reasoning?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18517", "title": "Imprinting: Knowledge Distillation Can Shift Student Behavior", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18484", "title": "ReTerm: Recovery Training for Self-Improving Terminal Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18472", "title": "Simplifying and Improving On-Policy Distillation for Few-Step Diffusion", "review_decision": "archived_source_exception", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18459", "title": "Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18162", "title": "LoOPSD: On-Policy Self-Distillation with Looped Teachers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "loopsd", "detail_path": "reproductions/2610.18162-loopsd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.18082", "title": "Failure Recovery via Belief Updates and World Modeling for Long-Horizon Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18067", "title": "WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18011", "title": "Correcting or Continuing? What On-Policy Distillation Learns from Student Errors", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18010", "title": "Fish Audio Drama 3 Technical Report", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17994", "title": "Improving Neural Symbolic Regression with a Diverse Prior and Post-training Alignment", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17900", "title": "PaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17767", "title": "Efficiently Learning To Reason or Not to Reason: Root-token Policy Optimization for Adaptive Thinking", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17666", "title": "DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17654", "title": "Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17616", "title": "StateHarness: Maintaining Evolving Project State for Long-Horizon Coding Agents", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17471", "title": "Scaling Inference-Time Compute with Teams of Coding Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17444", "title": "The belief-action gap in language model agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17409", "title": "Position: Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17370", "title": "HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17309", "title": "StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17113", "title": "Calibrated Typed Decisions for Entity, Relation, and Event Extraction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16867", "title": "Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16794", "title": "TPPO: Tracking-Value PPO For Language Model Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16354", "title": "Self-Distillation with Verbal Regularization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16104", "title": "SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15888", "title": "Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15368", "title": "ANTE: Anticipate, Then Execute -- Learning Internal World Models for Coding Agents from Verified Beliefs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15258", "title": "Sequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15244", "title": "EvolvAttack: Backdooring self Evolving VLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15173", "title": "Physics Foundation Models for Efficient Control of Fluid Flows", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15033", "title": "What Drives AI Citations? Content, Retrieval and Model Knowledge in Generative Engine Optimization (GEO)", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14705", "title": "Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14572", "title": "Reward-Aligned Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14479", "title": "AphaVoice: Text-to-Speech Model for Aphasia Patient Simulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14448", "title": "KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14440", "title": "Target-ESS Tempered Policy Optimization (TETPO): Smooth Variance Control via Bridge Importance Sampling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13923", "title": "Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14163", "title": "AutoEnvScaling: Automating the Data Flywheel with Terminal Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13896", "title": "Structural Automata for Neural Semantic Parsing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13821", "title": "Can Language Models Learn When to Abstain? Policy Learning and Calibrated Answer Selection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13744", "title": "A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13353", "title": "EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13306", "title": "Structure-Aware Numerical Stabilization for Half-Precision Proximal Policy Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13257", "title": "CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "cast-opd", "detail_path": "reproductions/2610.13257-cast-opd/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/cast-opd-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13238", "title": "State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "state-opd", "detail_path": "reproductions/2610.13238-state-opd/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.13205", "title": "Rethinking Relative Policy Differences Transfer of On-Policy Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13058", "title": "Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13025", "title": "Evo$^2$: Evolving the Evolver through Weight-Harness Co-Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "evo2", "detail_path": "reproductions/2610.13025-evo2/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct12-evo2-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12885", "title": "Personalized Federated Direct Preference Optimization via LoRA Adapters", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12757", "title": "MADS: Multi-Agent Dialog Simulation for Robust Conversational Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12659", "title": "MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "magicbeanstalk", "detail_path": "reproductions/2610.12659-magicbeanstalk/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.12601", "title": "Reflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level Overfitting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12572", "title": "DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12566", "title": "Sample-Adaptive Zeroth-Order Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12420", "title": "A Unified Bellman Operator for Safety-Critical Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12403", "title": "ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12341", "title": "Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12274", "title": "HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12207", "title": "SciTBERT: A family of chronologically consistent language models for scientific and technological language processing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12201", "title": "SteerablePlex: Can We Steer Full-Duplex Models?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11854", "title": "GRPODropout: Less is More for Online Reinforcement Learning Rollouts", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "grpo-dropout", "detail_path": "post-training/2610.11854-grpo-dropout/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/grpo-dropout-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11659", "title": "DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "dial-opd", "detail_path": "post-training/2610.11659-dial-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/dial-opd-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11638", "title": "UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11519", "title": "Residual Advantage: Student-Relative Teacher Guidance for RL with Verifiable Rewards", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "residual-advantage", "detail_path": "post-training/2610.11519-residual-advantage/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/residual-advantage-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11451", "title": "SAIL: Scientific Agentic Intelligence via a Science-Aware Loop", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11423", "title": "Policy Alignment: New Signals for Membership Auditing in On-Policy Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11366", "title": "SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11352", "title": "RL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11332", "title": "ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "recal", "detail_path": "post-training/2610.11332-recal/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/recal-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11291", "title": "When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "semi-opd", "detail_path": "post-training/2610.11291-semi-opd/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/semi-opd-a100-20261010.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11247", "title": "Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "opd-learning-signals", "detail_path": "post-training/2610.11247-opd-learning-signals/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/opd-learning-signals-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11183", "title": "RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11167", "title": "PIVOT: Perplexity-Informed KD-to-RL Transition Scheduling for Vertical-Domain Few-Shot Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "pivot", "detail_path": "post-training/2610.11167-pivot/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/pivot-a100-20261011.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11111", "title": "Lapras: Latent Reasoning for Time Series Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11064", "title": "Measuring and Mitigating Solution Mode Collapse in RLVR", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10947", "title": "RH-Detect: A Unified Benchmark for Reward Hacking Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10932", "title": "World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10878", "title": "Stochastic Teacher Intervention for Agentic On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10536", "title": "Decoupling Exploration from Optimization in RLVR", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10447", "title": "A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10426", "title": "CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10422", "title": "Which Rollout Taught It That? BehaviorTrace and the Limits of Training-Data Attribution in Online RL", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10411", "title": "Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10407", "title": "SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10273", "title": "A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and Clipping", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09934", "title": "Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASR", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09804", "title": "BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10623", "title": "Recurrent Self-Improvement: Dynamic Cross-Loop On-Policy Distillation for Looped Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09684", "title": "From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09665", "title": "SAPD: Step-Aligned Privileged Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09639", "title": "On-Policy Distillation Teaches New Skills but Not New Knowledge", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09587", "title": "Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09247", "title": "An Informational Curse of Horizon in Goal-Conditioned Policy Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09227", "title": "Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09108", "title": "Convex-Concave Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10592", "title": "Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08773", "title": "AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08561", "title": "Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08448", "title": "Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08398", "title": "UP-MOPD: Update Projection in Multi-Teacher On-Policy Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08112", "title": "Energy-Aware Path Following: Comparative Analysis of Reinforcement Learning and NMPC for Electric Vehicles", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07898", "title": "FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07874", "title": "On-Policy Distillation with Negative-Policy Rollouts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07842", "title": "Privileged Context as Drift in On-Policy Self-Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07781", "title": "Quantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation Designs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07731", "title": "Learning to Retrieve via Reinforcement Learning in Embedding Space", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07730", "title": "SanSi: A Looped Typed Decision Model for System 1.5 Thinking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07704", "title": "Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07654", "title": "Does On-Policy Distillation for Safety Pose Backdoor Risks?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07545", "title": "Quality-Aware Self-Correcting Speech Translation on an Edge Device", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07405", "title": "What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07247", "title": "Learning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07226", "title": "Minimal Witness Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07212", "title": "Reward-Driven Learning under Prompt-Level Differential Privacy", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07177", "title": "CLM-as-a-Judge: Evaluating an Open Contrastive Decision Model on Public Judge Benchmarks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06851", "title": "Base Models Can Reason By Taking a Cue From Training Data", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06833", "title": "Towards Looped Models Done Right, Part II: Rethinking at Fixed Points", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06829", "title": "CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06804", "title": "Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06782", "title": "T-Search: An Open Agentic Retriever and Playground for Hard Multi-Step Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06744", "title": "ufakzeka-karar: An Open Turkish Typed-Decision Model with Order-Invariant Option Scoring", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06671", "title": "Learning What to Imitate: Entropy-Aware Distribution Mixing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06637", "title": "Long-Horizon Textual World Modeling through Structured Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06439", "title": "Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06105", "title": "Flash-OPD: Fast On-Policy Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06019", "title": "Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05974", "title": "Transfer-Stratified On-Policy Distillation for RL-Improved Reasoning Teachers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05954", "title": "MEND: RL For Flow Models via Proximal Velocity Matching", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05935", "title": "ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05745", "title": "Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07043", "title": "TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05481", "title": "CodeForge-MA: Execution-Verified Multi-Agent Learning with Language-Conditioned LoRA for Multilingual Code Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05446", "title": "Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05282", "title": "Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05265", "title": "Loopy: Low-Bit Quantization Framework for Looped Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05099", "title": "Small Agents with Semantic Search: Efficient Multilingual Code Localization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05070", "title": "Outcome-Guided On-Policy Self-Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04950", "title": "How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04914", "title": "Monitorability Disposition in Large Reasoning Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04899", "title": "Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04882", "title": "ResOPD: Tail Residualization for Sparse On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04754", "title": "FoSeRL: Formal Sequential Robustness Certification for Reinforcement Learning Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06962", "title": "Verdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04638", "title": "Policy as Data: Replay-Based Policy Dual Averaging via Advantage Regression", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04596", "title": "DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06947", "title": "FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04328", "title": "Bidirectional Preference Synthesis: Learning Prompt-Conditioned Preferences from Boundary Failures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04299", "title": "Questioning the Questions: Sustaining Self-Evolution in Reasoning Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04272", "title": "Rethinking Self-Distillation for Multi-Teacher Capability Merging", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03984", "title": "Teaching Agents to Code Reliably", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03880", "title": "Reinforcement Learning on the Discrete Composition Channel of a Crystal Generator: Validated Gains and Reward Hacking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03702", "title": "LESSER: Post-Training Data Selection with Output-Layer Gradients", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "lesser", "detail_path": "post-training/2610.03702-lesser/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03515", "title": "Learning from Repaired Reasoning: Root-Cause-Guided On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03454", "title": "Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03369", "title": "Mixture-of-Experts for Cryptocurrency Order Execution: Training Stability, Tail Risk, and Failure Modes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03185", "title": "Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02911", "title": "Probe the Harness: Setup Checks for Stale-Data RL Comparisons in Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02886", "title": "Misinformation Without Triggers: From Factual Answers to Downstream Decisions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02848", "title": "Permutation Robustness Is Not Enough: Action Collapse in Multi-Agent Transformer Policies", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02846", "title": "Understanding Enrichment in Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02808", "title": "ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02781", "title": "OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02766", "title": "Exact Memory-Time Optimization for Prefix-Cached Language Model Serving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02740", "title": "Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02700", "title": "Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02614", "title": "What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse Perspectives", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02554", "title": "Test-time Multi-agent Coordination by Decomposed Value Gradient Flow", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02505", "title": "Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02486", "title": "From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02466", "title": "SD-DPC: Sparse Dictionary Differentiable Predictive Control", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02444", "title": "Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02359", "title": "Lexicographic Multi-Objective On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02324", "title": "Slow-Fast Multi-Teacher On-Policy Distillation for Capability Preservation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02189", "title": "Generative modeling of intrinsically disordered protein regions by reinforcing sparse autoencoder features", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02173", "title": "Every Ablation Is a Dose: Counterweights and the Semblance of Self-Repair", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02140", "title": "Finetuning with Sampling: SFT Learns Better Than You Think", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02098", "title": "Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic Interpretability", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01955", "title": "Do Your Own Research: Learning to Forecast by Learning to Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01908", "title": "Same Reward, Different Skills: When Multimodal RL Learns to Look", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01892", "title": "Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01828", "title": "The Asymptotics of Language Model Alignment with Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01729", "title": "Function-Structured Reinforcement Learning with Executable Verifiers for Mathematical Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01560", "title": "AURAL: Adaptive Latent Reasoning with Joint Chunk for Speech Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01511", "title": "GAW-PO: Preference Optimization with Gradient-Aligned Token Weights", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "gaw-po", "detail_path": "post-training/2610.01511-gaw-po/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01399", "title": "Reusing Past Samples in Proximal Policy Optimization: When and How Does It Help?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01278", "title": "SCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01238", "title": "Mixture-Trained Merging for Unified Multi-Objective Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01161", "title": "My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "my-fault", "detail_path": "post-training/2610.01161-my-fault/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01128", "title": "Grounding Large Language Models in DSGE Simulators for Policy Generation and Forecasting", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00991", "title": "Adapter Thickets: Splitting an RLVR Budget Beats Concentrating It", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00988", "title": "Auditable Algebraic Counting Field for Cryptic-Pocket Detection from Apo Structures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00888", "title": "Match the Distribution, Not the Compute: Post-Training Multi-Token Prediction Heads", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00852", "title": "Child-Adapted Structured Phonological Representations for Interpretable Speech Sound Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14030", "title": "Rotate the Loop: Blockwise Conformality for Looped Transformers", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00767", "title": "Pre-training interventions, ex post facto: Grafting model beliefs across checkpoints", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00610", "title": "Explainable Suicide Risk Assessment on Social Media with Multi-Task QLoRA", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00574", "title": "Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00540", "title": "Assessing the Impact of Language Disparity on Multilingual Linguistic Ability in Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00385", "title": "FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00367", "title": "MoRA: MoE Pruning via Router Bias Learning and Expert Approximation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14022", "title": "OPMD: On-Policy Mechanism Distillation Beyond Output Supervision", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14001", "title": "PreSO: Privileged Representation Isolation for On-Policy Self-Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13998", "title": "Enhanced Trading Systems with Intelligent Market Analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06892", "title": "Axiom Satisfiability of Linear Rewards in Alignment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08819", "title": "HydroSphere: A Framework for Governed, Self-Healing Wastewater Infrastructure", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00256", "title": "Verification Pulses and the Cost of Escaping Wrong Consensus", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00202", "title": "When a Data Artifact Isn't a Shortcut: Causal Auditing of Synthetic RLVR Corpora", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00197", "title": "Comedic Fool's Gold: Reward Exploits and Countermeasures in Conversational Humor", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06874", "title": "Statistical Turbulence and High-Fidelity Disturbance Fields for Quadrotor Flight Control", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00096", "title": "FACET at WMT 2026 Automated Translation Quality Evaluation Task", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00047", "title": "Characterizing a Configuration Where Inference-Time PRM-Pruned Fragment Grafting Is Inert: Evidence from Three Reasoning LMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00035", "title": "Integrating Fairness and Explainability in a Multiple Instance Reinforcement Learning System", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20584", "title": "Player-1: Learning to Play from Synthetic Experience", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20573", "title": "Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20437", "title": "From Training to Escalation: Forensic Analysis and Local Recreation of RL/RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20394", "title": "What Should a Software Team Spend on Agents? Simulation-Based Cost Optimization of Mixed AI-Human Teams", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20388", "title": "From Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20344", "title": "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20312", "title": "Reflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20245", "title": "P2Patch: Exploit-Guided Vulnerability Repair", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20200", "title": "Drivers of LLM Consensus Formation Under Competing Incentives: A Simulation Study", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20193", "title": "SWE-Stream: Scaling Executable Training Data for SWE Agents via Progressive Construction and Elastic Streaming", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20099", "title": "EvalBuilder: Can LLMs Build Efficient Benchmarks?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20068", "title": "The Code of Theseus: Can Agents Rebuild Software from Recovered Design Documents?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20038", "title": "SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.20022", "title": "Memorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19999", "title": "A Strong Harness Narrows the Model Gap: A Comparative Evaluation for Legislative Document-to-XML Conversion", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19864", "title": "Euler: Towards Human-Centered Multi-Agent Mathematical Discovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19849", "title": "DeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19843", "title": "LAGO: Language Agents with Reusable Growing Options", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19836", "title": "EGCForest: Structured Agent Memory Organization for Enterprise Group Chats", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19820", "title": "ActionOPD: Distilling Decisions, Not Tokens", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19818", "title": "One Monitor Does Not Fit All: Formalism-Agnostic Runtime Verification for Agentic AI", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19698", "title": "RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19695", "title": "C3: Rethinking Process Supervision via Confidence-Guided Credit Correction in Multi-Turn Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19596", "title": "JevCoder: When Does Decision Delegation Pay Off in Code Repair?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19589", "title": "JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19581", "title": "XferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19566", "title": "Mission (Im)Possible: Towards Autonomous Discovery of Autopilot Logic Flaws in Open-Source Drone Frameworks", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19474", "title": "Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19472", "title": "MemCode: Discrete Semantic Representations for Long-Term Agent Memory", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19458", "title": "PFedMA: Who Should Join Next as Federated Multi-Agent Orchestration Evolves?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19433", "title": "EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19425", "title": "Evaluating Agentic Capabilities Before Post-Training: An End-to-End Approach", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19423", "title": "Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19422", "title": "AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19399", "title": "KoAGE: Do Large Language Models Know, Learn, and Coin Korean Neologisms?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19397", "title": "SERO: Learning from Executable Oracle Continuations for Long-Horizon Agentic Reinforcement Learning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19386", "title": "STRATA: Self-Maintaining Structured Experience Graphs for Self-Evolving Language Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19382", "title": "ixi-sLM: On-Device sLM for AI Call Agent Service", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19381", "title": "EvoWeave: Composing Reusable Agent Experience through Operation Level Graphs", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19376", "title": "DeLoop: Repeated Actions as Self-Supervision for Long-Horizon Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19368", "title": "OS-Bench: Evaluating SWE Agents on Cross-OS Code Migration", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19345", "title": "When Is Smaller Greener? Right-Sizing Language Models for Agentic AI", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19292", "title": "Whose turn is it? Context-guided model routing for stateful agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19223", "title": "Definition Grounding in Theory-Level Auto-formalization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19222", "title": "REPORT-OPS: Hybrid Evidence-Guided Reporting with Human-Supervised Refinement for HPC", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19158", "title": "AgentCIScope: Grounded Contextual Integrity Evaluation for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.19005", "title": "CyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18813", "title": "Self-Evolving Agent Harness", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18808", "title": "Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18760", "title": "Beyond the Verdict: Agentic Code Judging with Verifiable Feedback", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18684", "title": "Knowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents", "review_decision": "accepted", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18654", "title": "Kwai Summary Attention V2 Technical Report", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18652", "title": "AMemOps: Evaluating Memory Updates in Long Audio Streams", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18616", "title": "Knowledge Graphs as Files: An Agent Harness Where Tool Creation and Tool Use Co-Evolve", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18602", "title": "Auditing Future-Memory Use in Point-in-Time Language Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18522", "title": "Lost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18515", "title": "A Global View of How LLMs Value Human Time", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18507", "title": "The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18478", "title": "MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18427", "title": "Reliable Memory from Unstable Growth: Curating Self-Written Agent Playbooks with Randomized Experiments", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18408", "title": "Prompt-Injection Probes Learn the Conversation, Not Just the Injection", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18378", "title": "Delegating Earth science model calibration to knowledge-guided LLM agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18356", "title": "Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18354", "title": "Choosing LLMs for Strategic Agent Interactions", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18305", "title": "AffectWorld: Benchmarking Emotion-Driven Future World Prediction", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18240", "title": "Beyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18229", "title": "When Does Opponent Modeling Pay Off? Spatial Inference Stabilises Reinforcement Learning under Partial Observability", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18206", "title": "SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18186", "title": "Reinforcement Learning for Large-Scale Lifelong Multi-Agent Path Finding with Shared Spatial Fields", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18097", "title": "APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18092", "title": "LifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18083", "title": "AReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18052", "title": "Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18007", "title": "Cost-Efficient Privacy Enforcement for Email-Generating LLM Agents under Strategic Information Requests", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18004", "title": "SWEPatchTest: Evaluating Software Tests Beyond Reproduction", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17928", "title": "Learning How to Remember: Memory Modality Selection for GUI Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17926", "title": "CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17869", "title": "ECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17861", "title": "State-Aware Generation of Deployable Websites from Visual Prototypes and Requirements", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17860", "title": "Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.18927", "title": "Why Static Skill Inconsistencies Do Not Equate to Runtime Risks: A Behavioral Analysis of LLM Agent Execution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17837", "title": "ProtoArena: Can AI Agents Discover and Exploit Real-World Cross-Component Protocol Vulnerabilities?", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17832", "title": "Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17816", "title": "Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17763", "title": "Memory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17757", "title": "Instructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17740", "title": "Coupled Harness--Model Evolution for Scientific Equation Discovery", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17724", "title": "Evidence-First Agentic Verification", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17723", "title": "Upstream Influence, Downstream Re-Anchoring in LLM Agent Chains", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17710", "title": "Adaptive-Group Process Rewards for GUI Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17694", "title": "HelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17670", "title": "Cowork-Gym: Synthesizing Interactive Work Environments at Scale", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17659", "title": "Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17627", "title": "AiSAQ-in-Filtering for DRAM-free Filtered Information Retrieval", "review_decision": "rejected_or_out_of_scope", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17613", "title": "MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17436", "title": "SchemaWeaver: Accelerating On-Device Mobile Agentic AI via Schema-Guided Parallel LLM Decoding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17418", "title": "Why Agentic Workflows Fail: A Taxonomy Derived from Literature and Empirical Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17374", "title": "VulnBump: A Benchmark for Fixing Vulnerable Dependencies in Real Projects While Keeping the Build and Tests Green", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17365", "title": "When Goals Leak Across Relationships: How Cached Goal Representations Shape Cross-Client Decisions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17310", "title": "Beyond Successful Play: Diagnosing Opponent Modeling in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17224", "title": "CodeLift: Your Test Suite Is Secretly a Dense SWE Curriculum", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17206", "title": "AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17197", "title": "Deleting Code Without Losing Knowledge: Regenerative Software for Python Libraries", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17195", "title": "Welcome to the Age of Agent Ads: Using On-Policy Attacks to Steer Agentic Decisions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17183", "title": "ChemExplain: A Multimodal Benchmark for Explanatory Chemical Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17130", "title": "EvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17114", "title": "D-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17043", "title": "Neos: Learning to Interleave Search and Visual Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.17020", "title": "CWE-bench: Refocusing Agentic Security from Exploitation to Defense", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16998", "title": "Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16975", "title": "MADDIE: Multi-Agent Drug Discovery Engine", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16946", "title": "Social Priors: Descriptions of AI Users Shape How Language Models Trust and Cooperate", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16919", "title": "ML Engineering Agents - A Data Management Perspective", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16911", "title": "Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16895", "title": "Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16870", "title": "SpecGuardBench: Can Coding Agents Construct Reliable Validation Harnesses from Natural Language Specifications?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16838", "title": "Same Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16725", "title": "Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16661", "title": "Structural Baselines Matter for Agent Failure Detection and Attribution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16632", "title": "REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16625", "title": "LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16498", "title": "From Caricature to Collective Artifact: How Persona Construction Drives Polarization in Generative Social Simulations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16450", "title": "CivWorldBench: Evaluating Language World Models in Structured Multi-Agent Sandbox Worlds", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16426", "title": "AuthGateBench: Benchmarking LLMs as Authorization Gate", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16412", "title": "SLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16402", "title": "EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16333", "title": "TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16315", "title": "ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16297", "title": "SLDBench v2: Active Scaling Law Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16251", "title": "Avoiding What Your Teacher Already Knows: Entity Familiarity for Deep-Search Distillation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16231", "title": "Learning to GUIDE the Group: Self-Learning LLM Facilitation Across Multi-Party Tasks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16224", "title": "Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16175", "title": "ProCARE: Real-World Study Automation via Profile-Grounded Evidence Contracts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16155", "title": "Uncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16140", "title": "Large Language Model Assisted Transportation Planning through a Differentiable User Equilibrium Layer", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16137", "title": "Recall Begets Recall: Recurrent Memory Ranking for Personalized LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16117", "title": "Beyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16078", "title": "Heterogeneous Agentic Coevolution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16070", "title": "Understanding and Reducing Misalignment in Persuasion Optimization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16067", "title": "When Agent Evaluation Becomes Unreliable: An Empirical Study of Oracle Failures and Configuration-Dependent Measurement in an LLM Agent Benchmark", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16027", "title": "Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.16015", "title": "Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15994", "title": "Large language model-generated patterns for epidemiological modeling: a multi-benchmark evaluation framework", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15991", "title": "Revocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15969", "title": "PopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15964", "title": "Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15961", "title": "Unfair and Unsafe: Everyday Bias Triggers Emergent Misalignment", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15910", "title": "RIVO: Lightweight Adaptive Rerouting for Deep Research Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15882", "title": "Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15766", "title": "SurgiCLAW: An Interpretable Atomic-Skill Agent for Precision Robotic Micromanipulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15765", "title": "A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15750", "title": "Google Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15738", "title": "Visible but Not Avoided: State-Dependent Re-Proposal of Rejected Candidates in Catalog-Based LLM Optimization Loops", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15708", "title": "SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15691", "title": "FARL: A Fully Automated Pipeline of RL Interface and Solver Design", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15642", "title": "Recall What Is Missing: Composing Evidence from Long-Term Agent Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15567", "title": "Reviewing Beyond the Change: Repository Size and Existing Code Across Agent and Human Pull Requests", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15529", "title": "Agent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15492", "title": "When Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15481", "title": "SkillFusion: Towards Reliable Multi-Skill Composition for LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15459", "title": "When Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15415", "title": "Sensitivity or Criterion? Measuring and Moving When Language Models Act", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15298", "title": "CHEAR: Confusion-Hierarchy Evidence-Aware Reasoning for Cost-Efficient Human Activity Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15292", "title": "OntoAR-HAR: Ontology-Guided Agentic RAG with Personalized Memory for Human Activity Recognition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15246", "title": "ObsSpec: Accelerating Agentic Reinforcement Learning with Observation Speculation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15228", "title": "Words to World: Benchmarking LLMs in Interactive Physical Environments", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15208", "title": "PANINI-DR: Controlled Deep Research through Generative Semantic Workspaces", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15150", "title": "Harmony Harness: Multi-Objective Self-Evolution of Agent Harnesses", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "harmony-harness", "detail_path": "agent-research/2610.15150-harmony-harness/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.15137", "title": "When the Approved File Is Unchanged: Authority-Set Integrity for Deployment and Coding-Agent Approvals", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.15084", "title": "Self-Evolving Visual Agent via Margin Reward", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14966", "title": "SkillHorizon: Constructing Long-Horizon Agent Tasks through Skill Composition", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14960", "title": "Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14956", "title": "MCPDisCo: Seesaw-Mitigated Tuning for MCP-Native Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14918", "title": "SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14915", "title": "WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14900", "title": "TeachGrade: Training-Free Short Answer Scoring with Teacher Evidence", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14877", "title": "Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14855", "title": "PEAM: On-device Communication Agent for Personalized, Efficient and Autonomous Mobile Network Configuration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14852", "title": "Getting Space Right: Agentic Rewards for Image Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14823", "title": "AI-Native Product Management: A Vision", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14808", "title": "Testuary: Agentic Test Generation with Zero-Shot Parallelism", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14790", "title": "Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14777", "title": "LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14774", "title": "ProgAgent: Learning Tool Orchestration through Programmatic Training", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14772", "title": "How Should a Camera-First AI Agent Work?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14768", "title": "Do Modifications Made by Coding Agents Make Subsequent Software Maintenance Harder?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14740", "title": "TileCas: Cascading Kernel Development Across Programming Abstractions", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14736", "title": "Think in Strategies, Act with Tools: Traceable Agentic Optimization for Combinatorial Problems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14662", "title": "Does Failure Feedback Direct Agent Self-Modification?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14636", "title": "PEARL: Process-Experience Aware Reinforcement Learning for Multi-Turn Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14629", "title": "Executable but Unfaithful: Mock Object, Stub, and Assertion Generation by LLMs and Coding Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14615", "title": "Limitations on Autoregressive Token Generation via Sequential Sampling", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14576", "title": "Iterate on an LLM, Serve on an SLM", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14570", "title": "PsyMemBehav: Psychology-Informed and Memory-Grounded Two-Level Identity-to-Action Reasoning for Social-Media Behavior Simulation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14547", "title": "A Self-Defining Operator for Distributed Applications", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14538", "title": "A Stateful Research Information Infrastructure for Scientific Discovery", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14523", "title": "ScienceBuddy-PV: A Verifier-Governed Recursive Improvement Protocol for Panvascular Intervention Research", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14495", "title": "Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer Videos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14477", "title": "What Counts as the Same Task? Executable Contracts for Robustness Evaluation of Tool-Using Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14465", "title": "Co-adaptive Rule Routing and Constraining for Structured Knowledge Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14462", "title": "Rethinking SZZ Search Strategies: Lessons from Claude Code", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14428", "title": "Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14382", "title": "ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14381", "title": "ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14216", "title": "Cortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14186", "title": "Visualizing the World Model in an Agent's Value Function", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14161", "title": "Agentic Evolution of SQL Test Generators", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13886", "title": "X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14157", "title": "OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13841", "title": "Returning to Development States: When Full Sandbox Snapshots Help Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13772", "title": "MARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoS", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13737", "title": "SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13703", "title": "A Baseline Assessment for the Agentic Web Technology Stack", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13668", "title": "(When) Should a Software Factory be Lights-off? Benchmarking Code Review Agents on Bug Detection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13647", "title": "A-SAW: The Agentic Software Architecture Workflow", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13632", "title": "Humanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13594", "title": "MENTOR: Learning from Failure with On-Policy Pedagogical Intervention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13494", "title": "Humanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13481", "title": "Branching On-Policy Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "branch-opd", "detail_path": "reproductions/2610.13481-branch-opd/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/branch-opd-a100-20261012.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.14130", "title": "Conserved amount, negotiable placement. Prompting perturbs one architecture, an AI reviewer both", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13455", "title": "Agentic Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13439", "title": "Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13438", "title": "Rollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13421", "title": "REINS: Agent-guided Thread Scheduling for Concurrency Bug Detection and Reproduction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13416", "title": "Web$hell: A Unified Interface for Agentic Web Access", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13399", "title": "RegulaTutor: A Theory-Informed Framework for Long-Term Personalized Learning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13395", "title": "ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13361", "title": "AgentSWE: Can Coding Agents Build the Agent You Actually Want?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13356", "title": "SWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13314", "title": "NEAR: Neighborhood-Aware Residuals for Memory Retrieval", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "near", "detail_path": "reproductions/2610.13314-near/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct13-near-a30.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13296", "title": "PRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13277", "title": "Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "beyond-final-embedding", "detail_path": "reproductions/2610.13277-beyond-final-embedding/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": "docs/gpu-validations/oct13-beyond-final-embedding-a30.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.13273", "title": "Agent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13267", "title": "Forgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13227", "title": "Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13172", "title": "RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13166", "title": "Scaling Agentic Data for Long-Horizon Terminal Intelligence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13152", "title": "Quality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13144", "title": "Competence-Aware Orchestration for LLM-Based Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13116", "title": "DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13092", "title": "When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "jev-workflow", "detail_path": "reproductions/2610.13092-jev-workflow/README.md", "document_exists": true, "registered_executable": true, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.13071", "title": "CAPE - Context-Aware Prioritization Engine for Vulnerability Scoring and Management", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13065", "title": "TestSuiteBench: Coding Agents Struggle to Generate Strong Test Suites from Specifications", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.13022", "title": "Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12957", "title": "JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12932", "title": "SEEDS: Preview-Guided Evidence Admission for Search Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12927", "title": "Collaborative Learning and Reasoning over Model Slices", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12849", "title": "Co-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12822", "title": "Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12789", "title": "EvoBelief: Falsifiable World Models for Self-Improving LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12655", "title": "CLEAT: Learning Value-Guided Clarification for Interactive Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14096", "title": "SWEeper-Bench: Can Agents Discover Bugs in Interactive Software?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12611", "title": "SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12598", "title": "Beyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12593", "title": "Know What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12569", "title": "SWE-Duel: Towards a Self-Scaling Arena for Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12300", "title": "Compact and Efficient Indexes for Learned Sparse Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12289", "title": "TestPrism: Rethinking Test Evaluation Beyond a Single Reference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12269", "title": "Cadence: Strategic Guidance for Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12243", "title": "NativeScope: Relation-Localized Retrieval over Native Topology with a Correct Anchor", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12135", "title": "Q-Shaped Options for Hierarchical Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12124", "title": "Use and Disuse: Intent-Structured Experience Consolidation for Memory and Learning in LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "hippocam", "detail_path": "agent-research/2610.12124-hippocam/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/oct10-hippocam-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.12090", "title": "Recompose and Refine Latent Reasoning Flows for Vision-Language-Action Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12086", "title": "EvoAlloc: A Self-Evolving Resource Allocation Agent for Efficient Program Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "evoalloc", "detail_path": "agent-research/2610.12086-evoalloc/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/oct10-evoalloc-a100.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.11963", "title": "Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11862", "title": "LEVER: Adaptive Cost-Aware Proof Search Over AND/OR Graphs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11858", "title": "Trajectory-Guided Fault Localization for Agent Skill Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11773", "title": "Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11768", "title": "Narrow and Deep: An Ontology Tower as the Knowledge of an LLM Agent for an Industrial Equipment System", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11732", "title": "MemTrial: Learning When to Trust Memory in LLM Portfolio Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11725", "title": "Implementing the Spec Growth Engine: Preventing Spec-Code Divergence, and Growing the Spec with Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11716", "title": "4-Tensor Attention Model for Semantic Physical Reality", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11707", "title": "DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11696", "title": "A 3D Characterization Framework for Intelligent Sequential Decision Making", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11663", "title": "Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11651", "title": "Evidence-Traceable Dynamic Interviewer Architecture for Expertise-Adaptive Qualitative Interviews Using Local LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11650", "title": "SkillContrast: Difference-Guided Text Selection for Agent Skill Reranking", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11647", "title": "One Skill Too Many: How Co-Installed Skills Conflict in Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11618", "title": "PolyCodeEval: Benchmarking Multilingual Code Generation from Functions to Repositories", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11617", "title": "TAM: Task-Aware Memory Distillation for Efficient Spatiotemporal Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11602", "title": "Where Do the Tokens Go? Understanding and Reducing Costs in LLM Agents for Vulnerability Discovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11600", "title": "Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11593", "title": "Runnable Commit Untangling for Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11573", "title": "Memory Type Varies: Empowering LLM Agents for Long-Term Memory with Diverse Strategies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11561", "title": "Workerville: Towards an Organizational Behavior Account of Agent Safety", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11552", "title": "Safe, Persistent, and Evolving Agent Harness for Understanding Partially Observable Worlds", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11546", "title": "Learning to Orchestrate Evolutionary Search: Progression-Aware Deep Reinforcement Learning for Dynamic DE-CMA-ES Coordination in Optimization and Structural Model Updating", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11523", "title": "When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11514", "title": "SSCBench: Evaluating the Evidential Validity of Fault-Injection Tests for Tool-Using LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11384", "title": "Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11370", "title": "RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11345", "title": "SynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11334", "title": "ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11312", "title": "MedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11299", "title": "DuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11253", "title": "LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11188", "title": "What to Admit and How to Present: Governing Persistent Memory in LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11179", "title": "Who Pays the Review Cost? Triage, Fairness, and Accountability in AI-authored Pull Requests", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11171", "title": "VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11169", "title": "Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11123", "title": "When Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.11008", "title": "Why LLM Agents Favor Their Group: Stakes, Observed Norms, and Reputation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10962", "title": "iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10961", "title": "Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10926", "title": "Adaptive Multi-Discriminator WGAN Framework for Resource-Constrained Internet of Vehicles Using Reinforcement Learning and Game Theory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10906", "title": "Reading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10768", "title": "Strategic Investment Decision Making for Value Creation in Energy Transition: A Reinforcement Learning Approach", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10740", "title": "Conversational Task Disambiguation over Tabular Data: Leakage-Aware Formulation, Benchmark Suite, and Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10538", "title": "Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10507", "title": "RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10478", "title": "Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10659", "title": "Applying Security by Design at the Point of Execution: How Governed Security Requirements Affect the Security of AI-Generated Code", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10320", "title": "LLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical Devices", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10302", "title": "Continual Graph Multi-Agent Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10265", "title": "Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10263", "title": "When Sub-Agents Work in Parallel: The Promises and Pitfalls of Dynamic Concurrency in Long-Horizon Coding Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10258", "title": "QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10256", "title": "OOM-RL II: Reality Is an Oracle, Not a Debugger Provenance-Constrained Diagnosis in Continually Evolving Agent-Engineered Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10242", "title": "TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent Ensemble", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10226", "title": "Why Software Engineering Is Indispensable in the Age of Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10206", "title": "Computations of the slice genus and the unknotting number of links via machine learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10184", "title": "Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10183", "title": "VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10164", "title": "UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10150", "title": "On the Reliability of LLM-Based Vulnerability Patching Benchmarks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10141", "title": "AdaT$^2$: Adaptive Test Transformations for Black-Box Boundary Testing of Conversational Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10126", "title": "Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10120", "title": "RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10091", "title": "ExperienceIndex: Artifact-Grounded Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10071", "title": "HGP:An on-device personalized agent memory via hybrid graph storage", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10062", "title": "Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10061", "title": "TRACK: Telemetry-Based Racing Analysis and Coaching Kit in Sim Racing Games", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10633", "title": "Has LLM Screening Performance Stalled in Software Engineering Systematic Reviews?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10042", "title": "Learning to Accumulate Knowledge with Mutual Information", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09995", "title": "Designing Collaborative AI-Driven Workflows for Scientific Software Engineering", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09973", "title": "From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10629", "title": "The Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09935", "title": "AgentTracer: Tracing Indirect Prompt Injection Attack through Fine-Grained Intention-Execution Alignment", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09870", "title": "Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10628", "title": "Agent4RE: A Self-Refining Multi-agent Framework for End-to-End Software Requirements Engineering and Benchmarking", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09856", "title": "Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09832", "title": "SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09824", "title": "Homogenization in Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09769", "title": "Bolzano: From Expert-Guided Proof Search to Automated Open-Problem Solving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09763", "title": "Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09683", "title": "System Switch: When Should a Fast Decision Model Stop and Think?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09681", "title": "Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09643", "title": "CircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09633", "title": "Coding-Agent Benchmarks Should Match Their Users' Task Flows", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10619", "title": "TestJack: Should you trust the results in coding benchmarks? Agentic Coding Benchmarks Auditing via Evaluator Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09590", "title": "Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09581", "title": "Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10612", "title": "PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10610", "title": "Code Understanding is a Bottleneck for Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09484", "title": "MIMESIS: Learning User Simulators as Training Environments for Interactive Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09466", "title": "LLM-Enabled UAV Dispatch: A System-Level Survey and Taxonomy", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09400", "title": "TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedback", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09374", "title": "DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10608", "title": "From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09348", "title": "Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10604", "title": "Beyond Type-checking: Towards Holistic Evaluation of Formal Specification Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09296", "title": "The AI Evaluation Ecosystem", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09267", "title": "Who Broke Me? Execution-Guided Repair of Behavioral Dependency Breaks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09264", "title": "Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09243", "title": "We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09218", "title": "RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09163", "title": "ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09159", "title": "SpecGuard: Proving a Task Is Broken Before the Agent Cheats", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "specguard", "detail_path": "agent-research/2610.09159-specguard/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": "docs/gpu-validations/specguard-a100-20261021.json", "gpu_receipt_valid": true, "capability_claim_verified": false } ] }, { "id": "2610.09146", "title": "Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09142", "title": "Finding Blind Spots in AppWorld and WorkArena Task Verifiers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09141", "title": "A Cognitive-Aware QML-CRL Framework for Detecting Affinity and Romance-Investment Fraud", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09139", "title": "Breaking the Space Barrier and its Application to Language Model Inference", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09127", "title": "CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09120", "title": "The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09112", "title": "GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09053", "title": "Justice After Identity: Large Language Models and the View from Everywhere", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09021", "title": "Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09008", "title": "Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.09000", "title": "How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08928", "title": "Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08901", "title": "Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08775", "title": "Agent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08720", "title": "WorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08691", "title": "ScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social Sciences", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08668", "title": "Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08662", "title": "ParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic Coding", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08651", "title": "A Case Study in Assuring AI-Written Software", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08622", "title": "Agentic RCA for Internet-Scale Services Using Constrained Creativity", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08621", "title": "Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08586", "title": "MINDSET: Energy-based Schema Evolution for Long Conversational Agent Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08553", "title": "DeltaTTT: Layerwise Optimization for Nonlinear Recurrent Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08514", "title": "How Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08430", "title": "NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08364", "title": "Transect: Retaining Observability for Long-Horizon LLM Agent Evaluations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08327", "title": "MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08250", "title": "MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08215", "title": "Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08155", "title": "Token-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of Labor", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08138", "title": "Test-Time Agent Evolution for Long-Horizon Legal Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08106", "title": "ChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy Specifications", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08101", "title": "Beyond Corrected Memory: Execution Consistency in Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08097", "title": "When Tools Lie: Reliability of Mathematical Agents Under Corrupted Tool Feedback", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08076", "title": "SpeedrunBench: Challenging LLM Agents with Video Game Speedrunning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08881", "title": "Mitigating Uncertainty Interactions in GenAI-based Adaptive Systems: Vision, Challenges and Preliminary Guidelines", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07984", "title": "Decide Before You Look: Learning Which Retrieved Memories Deserve Pixels", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07972", "title": "Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07937", "title": "Leveraging a four-quadrant approach for evaluating Redpine Science", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07935", "title": "SIGMA: Self-Improving Alignment Generalization from a Model Spec", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07886", "title": "ShanLiangRen: A Nutrition Agent for Personalized Daily Meal Planning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07881", "title": "Self-Referenced Social Preferences: Cooperation without Observing Others Rewards", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07862", "title": "A self-learning scientific agent for X-ray diffraction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07860", "title": "WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestration", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07851", "title": "RA-MoWE: Workflow-Affinity Embeddings for Query Clustering and Agentic Workflow Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07835", "title": "DHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07816", "title": "Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07787", "title": "OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08871", "title": "CredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07763", "title": "ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07757", "title": "Acquiring and Verifying Repository Norms for Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07753", "title": "From Evidence to Action: How Tool-Using Agents Fail", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07751", "title": "How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07725", "title": "PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10580", "title": "A Survey on LLM-Integrated Hardware Design Verification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07645", "title": "SkillPoison: Progressive Skill Poisoning via Successful Experiences", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07640", "title": "Towards the Automatic Synthesis of Interpretable Chess Tactics", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07639", "title": "HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07615", "title": "AFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget Constraints", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07594", "title": "BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07578", "title": "Cooperating with Future Collaborators: Multi-Agent RL under Staggered Participation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07570", "title": "Unanimously Wrong: Certified Abstention from How Medical LLM Consensus Forms", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07557", "title": "CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07556", "title": "Decoupled Multi-Agent Orchestration", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07550", "title": "Foundation Model-Aided Multi-Agent Reinforcement Learning for Wireless Random Access Network Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07534", "title": "The EPIC Framework for Spec-Driven Development", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07491", "title": "Who Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07475", "title": "Adapting to Changes in Agent Behavior via Finite-Depth Policy Sensitivity", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07473", "title": "PsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07423", "title": "2d-fet-bench: from spatial reasoning to fet design on flakes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07403", "title": "Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07376", "title": "MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07359", "title": "Evaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07350", "title": "Trajectory-Retrieval Speculative Decoding: When Does a Model's Own History Help?", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07311", "title": "Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07309", "title": "The Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07289", "title": "Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07261", "title": "Verifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling Planner", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07191", "title": "Agentic Design Space Exploration for Joint Hardware Configuration Selection and Mapping of AI Inference Workloads on Heterogeneous Edge SoCs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07184", "title": "Learning Scientific Exploration from Human Research Decision Trajectories", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06790", "title": "Back to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06672", "title": "VideoTapestry: Query-Adaptive Memory Refinement for Multi-Agent Long-Video Understanding", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06651", "title": "Considering Context: When World Models Need Context Encoders", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06614", "title": "FREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06597", "title": "Can Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06584", "title": "Does AI Help Cyber Attackers or Defenders? Evidence from Nonpublic Vulnerabilities and Subsequent Attacks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06563", "title": "HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06454", "title": "AgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06411", "title": "From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06361", "title": "Capability-Driven Self-Evolution of Agent Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06320", "title": "CRAFTER: Causality-based Self-adaptation for Autonomous IoT Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06207", "title": "AI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06193", "title": "Correct Code, Broken Contributions? SWE-CC: Benchmarking Repository Policy Compliance for Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06192", "title": "Copies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06191", "title": "Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06190", "title": "Bridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06163", "title": "Where Did the Repair First Go Wrong? Localizing the Origins of Silent Failures in Agentic Vulnerability Repair", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06148", "title": "Reinforcement Learning-Based Optimization of Workload-Aware Power Delivery Networks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06122", "title": "Benchmarking Jailbreak Guardrails for Embodied Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06083", "title": "Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06047", "title": "Let the Agent Do It? How Software Practitioners Understand and Make Permission Decisions in Agentic AI Assistants", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06025", "title": "Grounded Joint-Attention Other-Play for Zero-Shot Coordination", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07075", "title": "CuratorMAS: Automating Dataset Curation via Multi-Agent Orchestration", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06001", "title": "AgentSpy: Making AI Agent Behavior Observable", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05981", "title": "Mechanizing the User's Eye: Pre-Registered Deployment of a Sabotage-Validated Fail-Plausible Observer in a Production LLM Agent Runtime", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05961", "title": "Strategic Multi-Agent Learning for Interpretable Action Valuation of All Players in Football", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05828", "title": "Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05750", "title": "Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05739", "title": "HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05709", "title": "Nexus: An Execution Fabric for AI Agents Across Cloud, Edge, and Devices", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05700", "title": "Voltic: Distinguishing Volatility from Stochasticity in Recurrent Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05697", "title": "From Token-Max to Outcome-Max: How You Use AI Determines Its Productivity", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05622", "title": "UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05586", "title": "AgentDoxx: Agentic Re-identification of Anonymized Text with Web Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05569", "title": "Factoriax: A GPU-Accelerated Factorio-Style Simulator for Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05563", "title": "G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05526", "title": "Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05489", "title": "SkillGATE: Gate-Aware Monte Carlo Tree Search for Skill Retrieval", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05473", "title": "Hierarchical Reinforcement Learning with Stable Temporal Abstraction for Language Model Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05461", "title": "AI Safety via Debate is Compromised by Cognitive Biases", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05437", "title": "TeleTune: Evolving Agent Skills From Offline Telemetry", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05399", "title": "Adaptive Code Revision Attacks on AI Pull Request Reviewers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05398", "title": "MMPostTrainBench: Benchmarking Autonomous Research for Multimodal Post-Training", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05383", "title": "Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05382", "title": "Harness-Search: Guiding Long-Horizon Search through Multi-Agent Coordination", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05369", "title": "AutoDP-LLM: Automating Data Pre-processing for Intrusion Detection Systems using Large Language Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05348", "title": "Search Engines Never Say No: How Frozen Agents React When the Retrieval Tool Refuses", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05319", "title": "Understanding the Hierarchical Structure and Functional Landscape of the Model Context Protocol Ecosystem", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05300", "title": "MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05295", "title": "Readable Before Actionable: Causal Tracing of Indirect Prompt Injection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05284", "title": "Fusion is the New Mutation: Bandit-Guided Evolution on Workflow Graphs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05241", "title": "StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05219", "title": "Safe Context Switching for Agents in the Wild: Mitigating Subspace Interference via Orthogonal Adaptation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05176", "title": "AECG: Asymmetric Experience Consolidation and Governance In Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05162", "title": "Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05132", "title": "SpecAgent: Empowering Program Verification with Agentic Synthesis of Formal Program Specifications", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05124", "title": "Memory Canonicalization: A Framework and Benchmark for Cross-Model Drift in Persistent LLM Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05119", "title": "LexiHorizon: Stabilizing Reinforcement Learning for Long-Horizon Deep Search", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05107", "title": "SearchJev: A Fast and Calibrated System-1 Model for Search Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.07004", "title": "Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05103", "title": "VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05047", "title": "Beyond Task Completion: Measuring Interaction Cost in Terminal User Interfaces", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05037", "title": "SparseCraft: Agentic Hardware-Software Co-Optimization for Sparse Computing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05036", "title": "Characterizing Security Effects of OSS Vulnerabilities in Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05030", "title": "EVISKILL: Grounding Skill Evolution in Replayable Evidence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.05009", "title": "Rethinking Tool Design for Agentic RCA: A Controlled Empirical Study", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04991", "title": "CIPO: Counterfactual Imagination Policy Optimization for Adaptive Tool Granularity Selection", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04977", "title": "Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04940", "title": "Software World Models: From Consequence Prediction to Decision Value", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04921", "title": "Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04916", "title": "PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04915", "title": "Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04889", "title": "ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04878", "title": "Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04868", "title": "From Memory to Guide: Spatio-Temporal Composer for Procedural Coding Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04864", "title": "Enhancing Long-Video VLM Embeddings with Query-Aware Streaming Latent Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04838", "title": "MemTrace: State-Consistent Memory for Long-Horizon Coding Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04832", "title": "Agent Skill Evolution: How Revisions Affect Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04802", "title": "Multi-Agent Spectrum Sharing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04794", "title": "Knowing the Store: What a Memory Backend Must Write Down Before an Agent Can Read It", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04779", "title": "Asymmetric Repository Lineage Modeling and Verifier-Guided Coordination in Concurrent AI Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04740", "title": "Toward a Locally Deployable Agentic Co-Scientist: Small-Model Planning for Early-Stage Drug Discovery", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04716", "title": "Towards Automatically Pruning Logging Code with Coding Agents: How Far Are We?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06966", "title": "APEX: Active Protection at Execution Boundaries for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04672", "title": "MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04658", "title": "RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04646", "title": "SEIS: Self-Evolving Inference Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04641", "title": "Back to the Future: Regressing Readability Features from LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04639", "title": "When Talk Isn't Code: Comparing LLM Agents That Simulate and Develop Software", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04611", "title": "Practical Runtime Enforcement of First-Order Temporal Requirements", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04589", "title": "StegoMemory: Agentic Memory Acts as Covert Steganographic Channel", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04575", "title": "From Probe Scores to Alarm Policies: Operational Validity of Activation Monitors for Language-Model Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04555", "title": "$\\mathrm{TRIZ}^{a}$: Guiding Agent Evolution from Pattern Recognition to Solution Invention", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04528", "title": "Quantifying Collusion Among Autonomous LLM Agents: A Statistical Analysis of the Collusion Wiki Incident", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04494", "title": "DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04488", "title": "Can LLM Agents Automate Reinforcement Learning for Text-to-Speech?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04438", "title": "RAGrasp: Geometry-Semantic Template Retrieval and Grasp Transfer", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04433", "title": "What Does a Harness Buy? Tokens, Mostly", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04432", "title": "Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04429", "title": "Asking Earns Nothing: Scoring the Decision to Act in BFCL Multi-Turn", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04418", "title": "CORE-RL: Confidence-Oriented Reliability Evaluation of Black-Box Reinforcement Learning Policies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04379", "title": "AgentPersonaBench: Benchmarking Persona-Driven User Simulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04378", "title": "COPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol Layers", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04375", "title": "Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04371", "title": "Functionally Equivalent or Not? Graph-Grounded Differential Surrogate Execution for Code Equivalence", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04366", "title": "Human Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04292", "title": "LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04262", "title": "CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04246", "title": "Benchmarking Psychological Dynamics in Generative Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04196", "title": "Asynchronous Is Nearly Free for Evolution Strategies on Long-Horizon Agentic Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04195", "title": "MemLeak: Cross-User Semantic Leakage in Multi-Tenant AI Agent Memory", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04178", "title": "SHarP: Saliency-based Pruning of Agent Harnesses", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04168", "title": "Agentic Cognitive Depth: Operational Criteria for Evaluating LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04133", "title": "Auditing Pairwise Equivalence Judgments: Self-Critique Effects and Diversity Measurement in Multi-Agent Hypothesis Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06923", "title": "RadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care Pathway", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04109", "title": "SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "seer-forecasting", "detail_path": "agent-research/2610.04109-seer-forecasting/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.04083", "title": "Self-Propagating Misalignment in LLM Agents, and Why Auditing or Disabling Memory Is Not Enough", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04053", "title": "The Cost of a Hop: Benchmarking NLIP and A2A", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06918", "title": "Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04040", "title": "Agent Policy-Value Audit: Separating Transition Composition from Event Selection in Financial LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.04012", "title": "Beyond the Parameter Monolith: Reconstructive Memories, Executable Skills, and Residual Assembly for Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03994", "title": "Solving VeriContest with a Lean-Backed Rust Verifier", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03969", "title": "How Do Coding Agents Optimize Software and Report Performance Validation? A Large-Scale Empirical Study of Open-Source Pull Requests", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03938", "title": "MLLMs Fail to Refuse when Using Tools Agentically", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03934", "title": "SGAnalog: An End-to-End Circuit Benchmark from Open-Source Silicon Tapeouts", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03902", "title": "When Evidence Changes: Evaluating Memory Repair and Re-reading in Language-Model Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03651", "title": "MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03634", "title": "Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "depgpo", "detail_path": "agent-research/2610.03634-depgpo/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.03631", "title": "NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03620", "title": "UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03604", "title": "Mastering Atari 2600 Games with Discovered Options", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.06910", "title": "GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03598", "title": "When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03591", "title": "HazardWeaver: Scientific Route Selection for Hazard Analysis Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03574", "title": "HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03564", "title": "Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03510", "title": "Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03476", "title": "MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03356", "title": "ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World Models", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03315", "title": "Lightweight, Rubric-Guided Trajectory Evaluation for Production AI Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03213", "title": "Toward SLM-based agentic task-tool intent matching", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03830", "title": "Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03153", "title": "EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03099", "title": "Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03089", "title": "Securing Computer-Use Agents Against Branch Steering Attacks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03056", "title": "MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03055", "title": "hacktrace: behavior-supervised detection of reward hacking during code generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03033", "title": "When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMs", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03020", "title": "DyadMem: A Long-Term Memory Benchmark of How Agents Work with Users", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03014", "title": "Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03010", "title": "Engineering Sustainable Agents: A Systematic Comparison of Agentic LLMs for Developer Workflows", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02952", "title": "GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial Testing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02945", "title": "Continual Graph Memory for Mathematical Research Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02928", "title": "Discriminating Fixture Coverage in Agent-Infrastructure Verification Suites", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02925", "title": "Positive-Unlabeled Learning for Agent Safety False Alarm Auditing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02885", "title": "PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test Time", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02867", "title": "TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification Control", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02847", "title": "Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02814", "title": "VeriPy Source-Preserving Verification and Compatibility Checking for Python Components", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03820", "title": "From Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02710", "title": "Self-Supervised Scaling of Terminal Environments for Scientific Domains", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02654", "title": "Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02638", "title": "Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02617", "title": "WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02588", "title": "Open-Endedness Bench: Measuring Epistemic Process from Agent Records", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02569", "title": "Pincer: Resource Authorization for Agents using a Digital Twin", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02542", "title": "How To Train Your World Model: Fine-tuning vs RAG for LM-based World Modeling", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02525", "title": "Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02523", "title": "Hypothesis-guided discovery of cognitive algorithms via program refinement", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02480", "title": "MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02478", "title": "Tropical Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02452", "title": "Reinforcement Learning Techniques for the Optimization of Target Polarization in Nuclear Physics Scattering Experiments", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02396", "title": "Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02387", "title": "SOLO: Certified-Recall Metric Similarity Search with Scan-Only Sampled Inverted Lists", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02376", "title": "Coco: An Agentic Copilot for the Hardware--Software Co-Design Lifecycle", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02369", "title": "Automating the Application of HCI Principles: Skills for On-Demand UI Construction, the Human-AI Space to Think, and the Future of HCI", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02349", "title": "MIRROR: Multipath Quorum Integrity for LLM Multi-Agent Communication", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02330", "title": "Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02204", "title": "Reconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02202", "title": "ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02200", "title": "VISTA: A Visual Harness for Reasoning in an Interactive World", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02304", "title": "SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02161", "title": "DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02159", "title": "When Do Intrinsic Rewards Lead to Exploration?", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02074", "title": "Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02070", "title": "Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "causal-memory-policy", "detail_path": "agent-research/2610.02070-causal-memory-policy/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.02038", "title": "Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02012", "title": "Bellman Meets Lyapunov: Unsupervised Reinforcement Learning via Mastering Chaos", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.02005", "title": "Counting Moves, Weighing Voices: Bayesian Dialectical Argumentation for Calibrated Multi-LLM Councils under Persistent Adversaries", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01882", "title": "Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01833", "title": "Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01769", "title": "CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01564", "title": "Chaining Skills to Hijack LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01506", "title": "MCRI: A Four-Dimensional Framework for Analyzing and Evaluating Agent Skills", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01491", "title": "Auditing Web Agent Evaluation on WebArena-Lite: Human Review of Outcomes and Trajectories", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01451", "title": "A Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01415", "title": "Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "belief-state-pos", "detail_path": "agent-research/2610.01415-belief-state-pos/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01364", "title": "LLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01349", "title": "PACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "pace-capability", "detail_path": "agent-research/2610.01349-pace-capability/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01325", "title": "PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01256", "title": "DeFA: Dependency-Guided Failure Attribution for LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "defa", "detail_path": "agent-research/2610.01256-defa/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01207", "title": "Dependency-Aware Reward Shaping for Agentic Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "post-training", "key": "dars", "detail_path": "post-training/2610.01207-dars/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01195", "title": "Federated Agent Optimization", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01138", "title": "Auditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01102", "title": "MASkillBlender: Decentralized Whole-Body Coordination for Multi-Humanoid Loco-Manipulation via Skill Blending", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01093", "title": "OrbitTAMP: Grounding Language Models for Task and Motion Planning in Spacecraft Rendezvous", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01073", "title": "Safety Must Survive Self-Improvement: Why Failures Persist and How Agents Recover", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "safe-self-improvement", "detail_path": "agent-research/2610.01073-safe-self-improvement/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.01058", "title": "MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01045", "title": "Empty Commitments: When Agents Promise What They Cannot Deliver", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.01023", "title": "Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03796", "title": "ProsaBuddy: Assisting Mechanized Real-Time Schedulability Analysis with LLM-based Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00979", "title": "RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00977", "title": "ABSENTIA: Detecting Broken Access Control Vulnerabilities in Web Applications", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00972", "title": "VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "veriharness", "detail_path": "agent-research/2610.00972-veriharness/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00917", "title": "Finding the Right Fit: Model-Harness Interactions across Agent Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00905", "title": "Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00890", "title": "Cross-Benchmark Transfer from RL on Agentic Coding Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00885", "title": "FORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software Verification", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00872", "title": "MemFit: Efficient Long-Term Agentic Memory", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "memfit", "detail_path": "agent-research/2610.00872-memfit/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00870", "title": "An Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00849", "title": "Learning Multiple Timescales for Goal-Conditioned Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00758", "title": "Scalable Multi-Task Inverse Reinforcement Learning", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00710", "title": "ReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00705", "title": "Meta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00648", "title": "Incident-Arena: Getting agents to the last nine of reliability", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00629", "title": "ASAD: Adaptive Software Agents for Debugging", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00622", "title": "Understanding and Mitigating Library-Related Issues in LLM-Generated Code", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00619", "title": "Beyond Supra-Competitive Outcomes: Collusive Behaviour in Deep Reinforcement Learning for Optimal Execution Games", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00613", "title": "Spatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00590", "title": "Towards Hierarchical Cyber Defense with Large Language Models: From Planning to Execution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00557", "title": "No One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00511", "title": "Before Agents Decide: Epistemic Action in LLM-Based Systems", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00437", "title": "JevSpawn: Adaptive Agentic Inference through Compositional Action Spaces", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "catalogued", "observations": [ { "domain": "agent-research", "key": "jev-spawn", "detail_path": "agent-research/2610.00437-jev-spawn/README.md", "document_exists": true, "registered_executable": false, "gpu_receipt": null, "gpu_receipt_valid": false, "capability_claim_verified": false } ] }, { "id": "2610.00435", "title": "How AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00430", "title": "Memetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00425", "title": "Code That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00372", "title": "When Harnesses Lose the Signal: Causal Evaluation of Recovery in LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03780", "title": "OceanMind: A multi-agent AI system for ocean diagnosis", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00366", "title": "What Should an Agent Remember? Disentangling Retention from Retrieval in Bounded-Memory Evaluation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00354", "title": "Proof-Gated Signing: Solver-Checked Transaction Guards that Hold Under State Drift for Onchain AI Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.09549", "title": "SecureClaw: Clawing Back Control of LLM Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.11245", "title": "Position: Hippocampal Explicit Memory Is the Cornerstone for AGI", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2606.03031", "title": "AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.29893", "title": "Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.27860", "title": "C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.10337", "title": "CORTEG: Foundation Models Enable Cross-Modality Representation Transfer from Scalp to Intracranial Brain Recordings", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.09259", "title": "Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.10998", "title": "Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2605.06812", "title": "Towards Security-Auditable LLM Agents: A Unified Graph Representation", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.18344", "title": "DiffTSP: A Conditional Discrete Diffusion Model for Knowledge Graph Triple Set Prediction", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.02837", "title": "Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.02598", "title": "Explorable Proofs: Making Written Proofs Explorable by Grounding Them in Formal Representations", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.28317", "title": "Mapping data literacy trajectories in K-12 education", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.25216", "title": "A Wireless World Model for AI-Native 6G Networks", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.22519", "title": "LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.21854", "title": "Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2603.19514", "title": "Learning to Disprove: Formal Counterexample Generation with Large Language Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2604.08552", "title": "Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.08353", "title": "TKGB: A Comprehensive Benchmark for Temporal Knowledge Graph Forecasting", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2602.01779", "title": "LingLanMedBench: A Unified Benchmark for Evaluating Large Language Models in Traditional Chinese Medicine", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2601.22449", "title": "Emergence of Physical Intelligence via Controllable Information Production", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2511.23072", "title": "What If They Took the Shot? A Hierarchical Bayesian Framework for Counterfactual Expected Goals", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2510.06225", "title": "Generalized Multi-agent Social Simulation Framework", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2509.21712", "title": "It's My Agent, Not Me: Personal Privacy Boundaries in AI-Delegated Information Sharing", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2509.09498", "title": "SEDM: Selective Self-Evolving Distributed Memory for Agents", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.14021", "title": "CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00313", "title": "Rules to Tools: Executable Checks for LLM Agents in Scientific Computing", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.03758", "title": "Global Evaluation of AI and NWP Precipitation Forecasts During Atmospheric River Events", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.12496", "title": "An Input-Dependent Readout Phase for Resonant Sequence Models", "review_decision": "historical", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.10549", "title": "Synthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00188", "title": "Uncertainty-Aware RL-Controlled Adaptive 3D Mapping", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00182", "title": "Localizing Post-Wire Semantic Changes in MCP Agent Frameworks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00093", "title": "Safety in Self-Evolving Agents: A Survey", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00084", "title": "Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00015", "title": "From Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00012", "title": "When Do Causal World Models Help Modular LLM Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.00010", "title": "Heavy-Tailed Memory Traces in Long-Horizon Language Agents", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "2610.08793", "title": "Adaptive Workflow Intelligence: A Cognitive Architecture for Context-Driven Enterprise Automation", "review_decision": "known", "frozen_implementation_status": "existing_evidence_not_upgraded_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "official-google-catwild", "title": "CATWILD: Compiler Autotuning For TPU workloads in the Wild", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] }, { "id": "official-meta-autoformbench", "title": "AutoformBench: A Lean Formalization Benchmark for Advanced Mathematics", "review_decision": "reviewed_deferred", "frozen_implementation_status": "not_implemented_by_review", "current_status": "not_catalogued", "observations": [] } ] }