LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 14 days ago • 203
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding Paper • 2607.14935 • Published 14 days ago • 170
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use Paper • 2607.01874 • Published 28 days ago • 23
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 433
AnyMo: Geometry-Aware Setup-Agnostic Modeling of Human Motion in the Wild Paper • 2605.22715 • Published May 21 • 4
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? Paper • 2605.22109 • Published May 21 • 171