Token-Efficient Long Video Understanding for Multimodal LLMs Paper • 2503.04130 • Published 8 days ago • 76
Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation Paper • 2502.20388 • Published 14 days ago • 15
UniTok: A Unified Tokenizer for Visual Generation and Understanding Paper • 2502.20321 • Published 14 days ago • 29
SpargeAttn: Accurate Sparse Attention Accelerating Any Model Inference Paper • 2502.18137 • Published 16 days ago • 53
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning Paper • 2502.14768 • Published 21 days ago • 45
SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines Paper • 2502.14739 • Published 21 days ago • 97
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features Paper • 2502.14786 • Published 21 days ago • 129
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity Paper • 2502.13063 • Published 23 days ago • 66
Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs Paper • 2502.12982 • Published 23 days ago • 14
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published 25 days ago • 142
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU Paper • 2502.08910 • Published 29 days ago • 143