reward-guided-rl

Tag

Cards List
#reward-guided-rl

Reinforcing Few-step Generators via Reward-Tilted Distribution Matching

Hugging Face Daily Papers · 2026-05-25 Cached

RTDMD is a two-stage framework combining distribution matching distillation with reward-guided reinforcement learning to improve few-step image generation alignment with human preferences. It achieves state-of-the-art results on multiple models with only 4 inference steps.

0 favorites 0 likes
← Back to home

Submit Feedback