URSA-1.7B-IBQ512-UDM-GRPO Yovecents/URSA-1.7B-IBQ512-UDMGRPO-PickScore Text-to-Image • Updated about 1 month ago • 5 • 2 Yovecents/URSA-1.7B-IBQ512-UDMGRPO-GenEval Text-to-Image • Updated about 1 month ago • 3 • 2 UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models Paper • 2604.18518 • Published Apr 20 • 7
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models Paper • 2604.18518 • Published Apr 20 • 7
URSA-1.7B-IBQ512-UDM-GRPO Yovecents/URSA-1.7B-IBQ512-UDMGRPO-PickScore Text-to-Image • Updated about 1 month ago • 5 • 2 Yovecents/URSA-1.7B-IBQ512-UDMGRPO-GenEval Text-to-Image • Updated about 1 month ago • 3 • 2 UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models Paper • 2604.18518 • Published Apr 20 • 7
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models Paper • 2604.18518 • Published Apr 20 • 7