Awesome RL with Human Feedback / 2023 / arXiv

Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

作者：Chenfei Wu, Shengming Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang, Nan Duan · 单位：Microsoft Research Asia · 来源：arXiv · 发布日期：2023

多模态反馈文生图对齐框架/系统
新标签打开 AlphaXiv新标签打开 Code
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models figure
AlphaXiv 中文概览（可滚动查看）