23.08.14 (Mon)
RRHF: Rank Responses to Align Language Models with Human Feedback without tearsReinforcement Learning from Human Feedback (RLHF) facilitates the alignmentof
Feedback
2 articles
23.07.25 (Tue)
FABRIC 🎨Personalizing Diffusion Models with Iterative FeedbackDimitri Von Rüttefeedback으로 원하는 이미지 일관성 있게 생성모델에서 뽑아내기