ReCAST: Reward Credit Assignment across Timesteps for Online Diffusion Reinforcement
Paper • 2609.13425 • Published • 9
Hayeon Jeong
hayeon727
AI & ML interests
None yet
Recent Activity
upvoted a paper 4 months ago
AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment updated a dataset about 3 years ago
hayeon727/HowAreYouTodayOrganizations
None yet