Multimodal models

Back to the paper catalog

Paper titles link to the original publication when available. An English write-up is project documentation, not a claim of full reproduction.

Paper	First publication	Project write-up
UniAction: Unified Action Conditioning for World Models	2026-10-23	English · Chinese
FlexGlue: Sparse-to-Dense Feature Matching and Visual Disambiguation	2026-10-23	English · Chinese
Agentic World Action Models	2026-10-21	English · Chinese
Multimodal Reranking Is a System One Decision	2026-10-20	English · Chinese
CV-OPD: Contrastive Vision On-policy Distillation	2026-10-09	English · Chinese
WOVEN: Weaving Visual World Modeling into Multimodal LLMs	2026-10-08	English · Chinese
V-CoLA: Vision Token Compression with Linear Attention	2026-10-08	English · Chinese
Unsupervised Multimodal Reward Modeling	2026-10-08	English · Chinese
Mid-Training Language Models on Raw Video	2026-10-08	English · Chinese
Look Back, Think Ahead: Visual Memory on Demand for Efficient Multimodal Reasoning	2026-10-08	English · Chinese
EmbeddingGemma 2: Unified and Efficient Multimodal Representations	2026-10-06	English · Chinese
VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs	2026-09-15	English · Chinese
StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token Selection	2026-09-15	English · Chinese
From Visual Cues to Spoken Narration: Rethinking Audio Description	2026-09-01	English · Chinese
Editing Everything Everywhere All at Once	2026-06-30	English · Chinese
MVEB: Massive Video Embedding Benchmark	2026-06-12	English · Chinese
NaijaS2ST: A Multi-Accent Benchmark for Speech-to-Speech Translation in Low-Resource Nigerian Languages	2026-04-17	English · Chinese