Yihang Chen

YhangChen

2

·

https://yhangchen.github.io/

yhangchen

AI & ML interests

None yet

Recent Activity

upvoted a paper 1 day ago

ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement

authored a paper 1 day ago

Diffusion-based Cumulative Adversarial Purification for Vision Language Models

authored a paper 1 day ago

Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees

View all activity

Organizations

Papers 9

arxiv:2609.13425

arxiv:2506.03933

arxiv:2606.11189

arxiv:2502.12678

models 0

None public yet

datasets 0

None public yet