Hongyang Du
Hongyang-Du
AI & ML interests
3D Vision, Vision Language Model, Reinforcement Learning
Recent Activity
upvoted
a
paper
about 1 month ago
First Frame Is the Place to Go for Video Content Customization
upvoted
a
paper
3 months ago
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for
Synthetic Videos
upvoted
a
paper
4 months ago
Self-Rewarding Vision-Language Model via Reasoning Decomposition
Organizations
None yet