arXiv Machine Learning By Yuanshen Guan, Zipeng Feng, Zhiwei Xiong, Peiqin Sun

Latent Reward Registers for Diffusion Preference Alignment

Read the original on arXiv Machine Learning →

arXiv:2608. 03929v1 Announce Type: new Abstract: Aligning diffusion models with human preferences usually relies on a sparse terminal reward evaluated on the final generated samples, presenting a severe temporal credit-assignment challenge across the multi-step denoising process.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Aug 10

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression. We instead take an RL-native perspective: diffusion RL already generates reward-scored finite-step trajectories, whose intermediate states provide a natural source of distillation supervision rather than a disposable byproduct of sampling.

arXiv AI
Aug 11

RL-Native Distillation: Exploiting Scored Trajectories for Few-Step Image Generation

arXiv:2608. 09226v1 Announce Type: cross Abstract: Efficient text-to-image generation requires both reinforcement-learning (RL)-based reward alignment and few-step distillation, yet these procedures are typically performed sequentially, increasing training cost and risking the loss of reward gains during compression.

By Yuhan Li, Fangao Zeng, Sicong Kang, Mengfei Xu, Hao Zhou, Wei Li, Pipei Huang, Bingbing Ni