Awesome RL with Human Feedback / 2024 / arXiv

Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases

作者：Ziyi Zhang, Sen Zhang, Yibing Zhan, Yong Luo, Yonggang Wen, Dacheng Tao · 来源：arXiv · 发布日期：2024

奖励黑客/过优化奖励建模对齐目标设计文生图对齐
新标签打开 AlphaXiv新标签打开 Code
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases figure
AlphaXiv 中文概览（可滚动查看）