A General Theoretical Paradigm to Understand Learning from Human Preferences
Paper • 2310.12036 • Published • 19
Michal Valko
misovalko
AI & ML interests
large language models, reasoning, fine-tuning, test-time computation, reinforcement learning with human feedback, world models
Recent Activity
authored a paper 22 days ago
Language Generation with Replay: A Learning-Theoretic View of Model Collapse new activity about 1 month ago
paris-ai-running-club/README:Replace event upvoted a paper 4 months ago
A General Theoretical Paradigm to Understand Learning from Human
PreferencesOrganizations
upvoted a paper 4 months ago