ZiyiZhang27/tdpo

[ICML 2024] Code for the paper "Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases"

⭐ 38 ⑂ 0 Python MIT · 2024-07-12推送

https://icml.cc/virtual/2024/poster/32798

alignment diffusion-models reinforcement-learning rlhf stable-diffusion text-to-image human-feedback

38

Watchers

0

贡献者

0

Commits

0

Releases

1

Open Issues

2024-07-12

最近推送

原文中文

暂无 README