arxiv:2603.11784
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
1 day ago
Language Generation with Replay: A Learning-Theoretic View of Model Collapse new activity
16 days ago
paris-ai-running-club/README:Replace event upvoted a paper 3 months ago
A General Theoretical Paradigm to Understand Learning from Human
Preferences Organizations
