When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models Paper • 2604.08546 • Published Apr 9 • 115
MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens Paper • 2603.23516 • Published Mar 6 • 49
HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning Paper • 2603.17024 • Published Mar 17 • 109
Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding Paper • 2603.19235 • Published Mar 19 • 95
Towards Generalizable Robotic Manipulation in Dynamic Environments Paper • 2603.15620 • Published Mar 16 • 3
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Paper • 2603.12262 • Published Mar 12 • 31
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Paper • 2603.12262 • Published Mar 12 • 31
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously Paper • 2603.12262 • Published Mar 12 • 31