MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models
Paper
•
2511.18373
•
Published
•
6
•
2
Xiyang Wu PRO
wuxiyang
·
AI & ML interests
Reinforcement learning, Robotics, LLM
Recent Activity
upvoted
a
paper
about 2 months ago
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
published
a model
2 months ago
wuxiyang/MASS-LLaVA-OneVision-7B-Motion
published
a model
2 months ago
wuxiyang/MASS-Qwen25VL-7B-Motion
Organizations
commented
a
paper
2 months ago
commented
a
paper
7 months ago