large language models, reasoning, fine-tuning, test-time computation, reinforcement learning with human feedback, world models
News RSS feed
News: new Speaking at International #DataFestival in Yerevan: “Learning by bootstrapping: Reinforcement Learning”, September 2-3, 2023, Yerevan, Armenia. event
News: new Speaking at Matfyz Connections: “Mathematics of Large Language Models”, November 13, 2024, Bratislava, Slovakia. event
News: new Speaking at Sword AI Summit: “Aligning LLMs with human preferences”, November 9, 2024, Porto, Portugal. event
News: new Speaking at TEDx Humenné: “Llama 4 training”, November 15, 2024, Humenné, Slovakia. event
News: new Speaking at International #DataFestival in Yerevan: “Powerful LLM alignment”, September 12-13, 2025, Yerevan, Armenia. event
News: new Speaking at Newton's RL workshop, Nov 10-14, 2025, Isaac Newton Institute, Cambridge, UK. event
News: new Speaking at SlovakiaTech: “AI Innovations”, September 17–18, 2025, Kosice, Slovakia.
Bio
Michal is the Founding Researcher at Isara Labs, tenured researcher at Inria, and a lecturer at MVA at ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. He works on methods and settings that are able to deal with minimal feedback, such as deep reinforcement learning, bandit algorithms, self-supervised learning, or self play. Michal has recently worked on representation learning, world models and deep (reinforcement) learning algorithms that have some theoretical underpinning. In the past he has also worked on sequential algorithms with structured decisions where exploiting the structure leads to provably faster learning. Michal is now working on a new generation of large language models (LLMs), in addition to providing algorithmic solutions for their scalable test-time inference, fine-tuning and alignment. He received his PhD in 2011 from the University of Pittsburgh, before getting a tenure at Inria in 2012 and co-creating Google DeepMind Paris with R. Munos. In 2024, he became a Principal Llama Scientist at Meta, building online reinforcement learning stack and research for Llama 3. In 2025, he joined Isara Labs as a founding researcher.
Selected work
Research threads spanning frontier models, representation learning, bandits, and sparsification.
Nash-MD / NLHF
Preference learning as a two-player game, connecting LLM alignment, human feedback, and provable Nash-equilibrium algorithms.
NLHF · Nash-MD · preference learning
IX / implicit exploration
Implicit exploration replaces explicit exploration mixing with a biased loss estimator, giving sharp guarantees under partial and side-observation feedback.
side observations · data-dependent bounds · contextual bandits
Bandits & structured exploration
A long line on learning faster from structure: graphs, side observations, combinatorial actions, and Bayesian exploration.
Spectral · graph bandits · best-arm ID · semi-bandits · Thompson sampling
SQUEAK & sparsification
Single-pass sparsification of kernel matrices and graphs using ridge leverage scores, with scalable distributed variants.
Kernel approximation · ridge leverage scores · spectral sparsification
Coming up
Contact
Paris, France
40 avenue Halley
59650 Villeneuve d'Ascq, France
+33 3 59 57 78 01
4, avenue des Sciences
91190 Gif-sur-Yvette, France