UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Paper • 2604.18518 • Published • 7
JiaQi Wang
Yovecents
AI & ML interests
None yet
Recent Activity
liked a model 15 days ago
Yovecents/URSA-1.7B-IBQ512-UDMGRPO-PickScore liked a model 15 days ago
Yovecents/URSA-1.7B-IBQ512-UDMGRPO-GenEval submitted a paper 15 days ago
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion ModelsOrganizations
None yet
submitted a
paper to Daily Papers 15 days ago