arxiv:2609.13425
Kuei-Chun Kao
Johnson0213
AI & ML interests
MLLM agent/ Reward model
Recent Activity
authored a paper 12 days ago
ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement upvoted a paper 12 days ago
ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement