AI RESEARCH
Reinforcing Few-step Generators via Reward-Tilted Distribution Matching
arXiv CS.CV
•
ArXi:2605.26108v2 Announce Type: replace Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a two-stage framework that unifies distribution matching distillation with reward-guided reinforcement learning for few-step flow generators. We show that minimizing the KL divergence to a reward-tilted teacher distribution naturally decomposes into a distribution matching term and a reward maximization term.