2 papers
cs.LG2026
Latent Reward Registers for Diffusion Preference Alignment
Yuanshen Guan, Zipeng Feng, Zhiwei Xiong +2
Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, which creates a severe temporal credit-assignm…
cs.CV2024
Neural Degradation Representation Learning for All-In-One Image Restoration
Mingde Yao, Ruikang Xu, Yuanshen Guan +2
Existing methods have demonstrated effective performance on a single degradation type. In practical applications, however, the degradation is often unknown, and the mismatch betwee…