Awesome RL with Human Feedback / 2023 / arXiv

ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation

作者：Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, Yuxiao Dong · 单位：⋄Tsinghua University · 来源：arXiv · 发布日期：2023

偏好学习评测/基准多模态反馈文生图对齐
新标签打开 AlphaXiv新标签打开 Code新标签打开 Dataset
ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation figure
AlphaXiv 中文概览（可滚动查看）