Checklists Are Better Than Reward Models For Aligning Language Models
Vijay Viswanathan, Yanchao Sun, Xiang Kong, Meng Cao, Graham Neubig, Tongshuang Wu
De quem é
Appleafiliação declarada pelos autores, segundo o OpenAlex
Outros papers das mesmas organizações
- The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem ComplexityApple · 575 citações
- Diffusion Model-Based Image Editing: A SurveyAdobe Systems · 404 citações
- SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial UnderstandingApple · 236 citações
- MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced TrainingApple · 173 citações
- FastVLM: Efficient Vision Encoding for Vision Language ModelsApple · 168 citações
- Multimodal Autoregressive Pre-training of Large Vision EncodersApple · 147 citações