Hongyang Du's picture

4 1

Hongyang Du

Hongyang-Du

https://hongyang-du.github.io/

AI & ML interests

3D Vision, Vision Language Model, Reinforcement Learning

Recent Activity

authored a paper 1 day ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

upvoted a paper 2 days ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

liked a Space 8 days ago

thinkwee/BibGuard

View all activity

Organizations

None yet

upvoted a paper 2 days ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 3 days ago • 41

upvoted a paper 4 months ago

First Frame Is the Place to Go for Video Content Customization

Paper • 2511.15700 • Published Nov 19, 2025 • 53

upvoted a paper 5 months ago

VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos

Paper • 2505.01481 • Published May 2, 2025 • 4

upvoted a paper 7 months ago

Self-Rewarding Vision-Language Model via Reasoning Decomposition

Paper • 2508.19652 • Published Aug 27, 2025 • 84