AlignDiff: Aligning Diverse Human Preferences Via Behavior-Customisable Diffusion ModelZibin Dong,Yifu Yuan,Jianye HAO,Fei Ni,Yao Mu,YAN ZHENG,Yujing Hu,Tangjie Lv,Changjie Fan,Zhipeng HuICLR 2024(2024)引用 0|浏览1暂无评分关键词Reinforcement learning,Diffusion models,RLHF,Preference aligningAI 理解论文溯源树样例生成溯源树,研究论文发展脉络Chat Paper正在生成论文摘要