MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
Paper
•
2501.02955
•
Published
•
37
Zhuoyi Yang
zyyangzy
AI & ML interests
Multimodal learning
Recent Activity
authored
a paper
2 days ago
MotionBench: Benchmarking and Improving Fine-grained Video Motion
Understanding for Vision Language Models
authored
a paper
4 days ago
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning
for Image and Video Generation
Organizations
None yet
zyyangzy's activity
authored
a
paper
2 days ago
authored
a
paper
4 days ago
authored
a
paper
4 months ago