TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward
Paper • 2603.07700 • Published • 13
Tianyang Hu
whatlegequ
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward authored a paper about 1 year ago
Inducing Neural Collapse in Deep Long-tailed Learning authored a paper about 1 year ago
Elucidating The Design Space of Classifier-Guided Diffusion GenerationOrganizations
upvoted a paper about 1 month ago
upvoted 3
papers about 1 year ago
Learning Few-Step Diffusion Models by Trajectory Distribution Matching
Paper • 2503.06674 • Published • 8
The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
Paper • 2402.15170 • Published • 1
Rewards Are Enough for Fast Photo-Realistic Text-to-image Generation
Paper • 2503.13070 • Published • 10