Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL 事件

Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL arXiv:2605.24001v1 Announce Type: new Abstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the