MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
Paper
• 2511.18373 • Published
• 7 •
2
Xiyang Wu PRO
wuxiyang
·
AI & ML interests
Reinforcement learning, Robotics, LLM
Recent Activity
authored
a paper
3 days ago
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data upvoted a paper 3 days ago
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data upvoted a paper 3 months ago
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing Organizations
commented a paper 4 months ago
commented a paper 9 months ago