| 2609.12464 Beyond Vector Similarity: Hierarchical Context-Aware Graph RAG vs Standard RAG in Enterprise Code Migration |
Substantive review still needed; not accepted for implementation |
| 2609.01834 Architecting Conversational Data Systems for Stateless LLM APIs |
Substantive review still needed; not accepted for implementation |
| 2609.01588 Designing Proactive Thought Partners for Writing |
Substantive review still needed; not accepted for implementation |
| 2608.11367 Gaze Target Estimation Anywhere with Concepts |
Substantive review still needed; not accepted for implementation |
| 2608.05578 Detecting Safety Training Modification in Language Models via Activation Analysis |
Substantive review still needed; not accepted for implementation |
| 2607.25537 Visual prompt engineering for video models |
Substantive review still needed; not accepted for implementation |
| 2607.13614 VIP-MINGLE: A Corpus for Videoconference and In-Person Multimodal Interaction in Group Language Engagement |
Substantive review still needed; not accepted for implementation |
| 2607.02515 PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation |
Substantive review still needed; not accepted for implementation |
| 2606.00369 Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety Alignment |
Substantive review still needed; not accepted for implementation |
| 2606.00131 AI-PROPELLER: Warehouse-Scale Inter-Procedural Code Layout Optimization with AlphaEvolve |
Substantive review still needed; not accepted for implementation |
| 2605.30322 Gram: Assessing sabotage propensities via automated alignment auditing |
Substantive review still needed; not accepted for implementation |
| 2605.30174 LiveSVG: Zero-Shot SVG Animation via Video Generation |
Substantive review still needed; not accepted for implementation |
| 2605.29729 Realistic honeypot evaluations for scheming propensity |
Substantive review still needed; not accepted for implementation |
| 2605.26340 Scientist-One: Verifiable Autonomous Research via Chain-of-Evidence |
Substantive review still needed; not accepted for implementation |
| 2604.27723 Optimized Deferral for Imbalanced Settings |
Substantive review still needed; not accepted for implementation |
| 2604.23099 ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation |
Substantive review still needed; not accepted for implementation |
| 2604.20329 Image Generators are Generalist Vision Learners |
Substantive review still needed; not accepted for implementation |
| 2604.09803 MAGE: Modality-Agnostic Music Generation and Editing |
Substantive review still needed; not accepted for implementation |
| 2604.05364 TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems |
Substantive review still needed; not accepted for implementation |
| 2603.29791 Reasoning-Driven Synthetic Data Generation and Evaluation |
Substantive review still needed; not accepted for implementation |
| 2603.29470 AI-Simulated Expert Panels for Socio-Technical Scenarios and Decision Guidance |
Substantive review still needed; not accepted for implementation |
| 2603.28896 Fisheye3R: Adapting Unified 3D Feed-Forward Foundation Models to Fisheye Lenses |
Substantive review still needed; not accepted for implementation |
| 2603.24591 Vibe Coding XR: Accelerating AI + XR Prototyping with XR Blocks and Gemini |
Substantive review still needed; not accepted for implementation |
| 2603.14769 POLCA: Stochastic Generative Optimization with LLM |
Substantive review still needed; not accepted for implementation |
| 2603.14609 GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data |
Substantive review still needed; not accepted for implementation |
| 2603.10465 MoXaRt: Audio-Visual Object-Guided Sound Interaction for XR |
Substantive review still needed; not accepted for implementation |
| 2603.06981 Diffusion Controller: Framework, Algorithms and Parameterization |
Substantive review still needed; not accepted for implementation |
| 2603.01293 Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models |
Substantive review still needed; not accepted for implementation |
| 2602.17554 A Theoretical Framework for Modular Learning of Robust Generative Models |
Substantive review still needed; not accepted for implementation |
| 2602.16938 ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders |
Substantive review still needed; not accepted for implementation |
| 2602.12481 Online Advertising with Spatial Interactions |
Substantive review still needed; not accepted for implementation |
| 2602.07918 Causal Armor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution |
Substantive review still needed; not accepted for implementation |
| 2602.07266 ADCanvas: Accessible and Conversational Audio Description Authoring for Blind and Low Vision Creators |
Substantive review still needed; not accepted for implementation |
| 2602.06276 Learning from Attribution Sets |
Substantive review still needed; not accepted for implementation |
| 2602.02690 Outrunning LLM Cutoffs: A Live Kernel Crash Resolution Benchmark for All, |
Substantive review still needed; not accepted for implementation |
| 2602.02164 Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents |
Substantive review still needed; not accepted for implementation |
| 2601.21149 Mobility-Embedded POIs: Learning What a Place Is and How It’s Used from Human Movement |
Substantive review still needed; not accepted for implementation |
| 2601.19066 Dynamic Cogeneration of Bug Reproduction Test in Agentic Program Repair |
Substantive review still needed; not accepted for implementation |
| 2601.00372 LLM-Powered Analysis of IoT User Reviews: Tracking and Ranking Security and Privacy Concerns |
Substantive review still needed; not accepted for implementation |