Michal Valko

5

Papers

9

Total Citations

1

Affiliations

Affiliations

Building something new @ Stealth Startup & Inria & MVA - Ex: Llama @AIatMeta Gemini and BYOL @GoogleDeepMind

Papers (5)

Unlocking the Power of Representations in Long-term Novelty-based Exploration

Nash Learning from Human Feedback

Decoding-time Realignment of Language Models

Generalized Preference Optimization: A Unified Approach to Offline Alignment

Human Alignment of Large Language Models through Online Preference Optimisation