TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
Paper • 2603.07700 • Published • 13
Yifan Song
asmallhammer
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 months ago
TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward upvoted a paper 3 months ago
ViewFusion: Structured Spatial Thinking Chains for Multi-View Reasoning upvoted a paper 8 months ago
Reinforcing Diffusion Models by Direct Group Preference OptimizationOrganizations
None yet
upvoted 2
papers 3 months ago