michal.valko#inria.fr

, Founding Researcher at a startup, researcher at Inria, and a lecturer at MVA/ENS PS.

  large language models, reasoning, fine-tuning, test-time computation, reinforcement learning with human feedback, world models

News

News: new Game theory paper accepted to ICML 2025!
News: new I became the Founding Researcher at a stealth startup!
News: We released Llama 3, check it out!
News: Four LLM alignment papers accepted to ICML 2024!
News: I became a Principal Llama Scientist of Meta's GenAI in Paris!
News: IPO paper accepted to AISTATS 2024!
News: One RLHF theory and one exploration bonus paper at ICLR 2024!
News: Fast-forward ⏩ alignment research with Nash learning from human feedback!
News: Another RLHF result, these time includes learning rates for RLHF!
News: A new RLHF paper from our group!
News: An RL paper on learning rate randomization accepted to NeurIPS 2023!
News: BIG NEWS: Outstanding paper award at ICML 2023 for our game theory work!
News: Nine papers including two orals accepted to ICML 2023!

older news

Bio

Michal is the Founding Researcher at a stealth startup, tenured researcher at Inria, and the lecturer at MVA at ENS Paris-Saclay. Michal is primarily interested in designing algorithms that would require as little human supervision as possible. He is working 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, word 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 new generation of large large models (LMMs), in addition to providing algorithmic solutions for their scalable test-time inference, fine-tuning and alignment. He received his Ph.D. in 2011 from the University of Pittsburgh, before getting a tenure at Inria in 2012 and co-creating Google DeepMind Paris with Rémi Munos. In 2024, he became the scientist at Meta, building online reinforcement learning stack and research for Llama 3.

• 1-page resume
• long CV

Students and postdocs

• Giorgio Racca, 2025-2028, ETH, PhD student, with Amartya Sanyal

• Côme Fiegel, 2022-2025, ENS Ulm, PhD student, with Pierre Ménard and Vianney Perchet
• Daniil Tiapkin, 2023-2025, X, PhD, with A. Naumov, D. Belomestny, É. Moulines, P. Ménard
• Lisa Bedin, 2021-2025, École Polytechnique, PhD student, with É. Moulines
• Pierre Ménard, 2019 - 2020, ENS Rennes/U Toulouse, postdoc, with Emilie Kaufmann ↝ U. Magdeburg
• Édouard Oyallon, 2017 - 2018, ENS Rennes/ENS Ulm, postdoc ↝ EC Paris ↝ CNRS
• Dan Jarrett, 2022, University of Cambridge, visiting PhD student, with Corentin Tallec
• Jean Tarbouriech, 2019 - 2022, X/MVA, PhD student, with Alessandro Lazaric
• Omar Darwiche Domingues, 2018 - 2022, EC Paris/MVA, PhD student, with Emilie Kaufmann ↝ Owkin
• Xuedong Shang, 2017 - 2021, ENS Rennes, PhD student, with Emilie Kaufmann ↝ Barclays
• Pierre Perrault, 2017 - 2020, ENS Cachan/MVA, PhD student, with Vianney Perchet ↝ IDEMIA
• Julien Seznec, 2017 - 2021, ENS Ulm/MVA, PhD student, with Alessandro Lazaric ↝ Education Nationale
• Guillaume Gautier, 2017 - 2020, EC Lille/MVA, PhD student, with Rémi Bardenet ↝ Grenoble ↝ CNRS
• Jean-Bastien Grill, 2014 - 2019, ENS Ulm/MVA, PhD student, with Rémi Munos ↝ DeepMind
• Yunhao Tang, 2019-2020 and 2021, Columbia University, visiting PhD student, with Rémi Munos ↝ DeepMind
• Aadirupa Saha, 2019 - 2020, IIS Bangalore, visiting PhD student, with Pierre Gaillard ↝ Microsoft Research
• Kaige Yang, 2019, University College London, visiting PhD student, with Pierre Ménard ↝ VU Amsterdam
• Rianne de Heide, 2019, CWI/Leiden University, visiting PhD student, with Emilie Kaufmann
• Tomáš Kocák, 2013 - 2016, Comenius University, PhD student, with Rémi Munos ↝ ENS Lyon ↝ U. Potsdam
• Daniele Calandriello, 2014 - 2017, Polimi, PhD student, AFIA, 1st prize, with Alessandro Lazaric ↝ IIT ↝ DeepMind

• Côme Fiegel, 2022, ENS Ulm, M2 student, with Pierre Ménard and Vianney Perchet
• Daniil Tiapkin, 2021-2023, HSE, MSc. student, with Alexey Naumov, Denis Belomestny, Éric Moulines, and Pierre Ménard
• David Cheikhi, 2020 - 2021, Columbia University, NYC/École Polytechnique, Paris, with Pierre Ménard
• Robert Müller, 2020, Technical University of Munich, M2 student, with Pierre Ménard
• Ahmed Choukarah, 2020, ENS Ulm, L3 student, with Pierre Ménard
• Côme Fiegel, 2019, ENS Ulm, L3 student, with Victor Gabillon
• Axel Elaldi, 2017-2018, master student, École Centrale de Lille ↝ ENS Paris-Saclay/MVA
• Xuedong Shang, 2017, master student, ENS Rennes, with Emilie Kaufmann ↝ Inria
• Guillaume Gautier, 2016, master student, École Normale Supérieure, Paris-Saclay, with Rémi Bardenet ↝ Inria/CNRS
• Andrea Locatelli, 2015-2016, ENSAM/ENS Paris-Saclay, with Alexandra Carpentier ↝ Universität Potsdam
• Souhail Toumdi, 2015 - 2016, master student, École Centrale de Lille, with Rémi Bardenet ↝ ENS Paris-Saclay/MVA
• Akram Erraqabi, 2015, master student, École Polytechnique, Paris ↝ Université de Montréal
• Mastane Achab, 2015, master student, École Polytechnique, Paris, with G. Neu ↝ l'ENS PS ↝ TPT ↝ UPF Barcelona
• Jean-Bastien Grill, 2014, master student, École Normale Supérieure, Paris, with Rémi Munos ↝ Inria
• Alexandre Dubus, 2012-2013, master student, Université Lille1 - Sciences et Technologies ↝ Inria
• Karim Jedda, 2012-2013, master student, École Centrale de Lille ↝ ProSiebenSat.1
• Alexis Wehrli, 2012-2013, master student, École Centrale de Lille ↝ ERDF

Contact

• Stealth Startup
• San Francisco, California, US
• London, UK

• Inria Lille - Nord Europe, equipe Scool (bureau: A05)
• Parc Scientifique de la Haute Borne
• 40 avenue Halley
• 59650 Villeneuve d'Ascq, France
• office phone: +33 3 59 57 7801

• Centre Borelli, ENS Paris-Saclay (bureau: vacataires)
• 4, avenue des Sciences
• 91190 Gif-sur-Yvette