Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yibin, Li, Zhimin, Zang, Yuhang, Zhou, Yujie, Bu, Jiazi, Wang, Chunyu, Lu, Qinglin, Jin, Cheng, Wang, Jiaqi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.20751