avatar

Edouard Leurent

Senior Research Scientist
Google DeepMind
eleurent (at) gmail.com


eleurent's Github Chart

About Me

Hi! I am a Senior Research Scientist at Google DeepMind, working on Gemini and generative models.

Research Interests

Work and publications

  1. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.
    PDF Project Page

  2. Google I/O
    Gemini Diffusion
    Presented at Google I/O 2025, and on The Keyword (Google Blog)
    Project Page

  3. EMNLP
    Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning
    Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Avinava Dubey, Alexandre Ramé, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Léonard Hussenot, Olivier Bachem, Edouard Leurent
    Findings of the 2024 Conference on Empirical Methods in Natural Language Processing
    PDF BibTex

  4. Gemini: A Family of Highly Capable Multimodal Models
    Gemini team
    PDF BibTex

  5. Nature
    Faster sorting algorithms discovered using deep reinforcement learning
    Daniel J. Mankowitz*, Andrea Michi*, Anton Zhernov*, Marco Gelmi*, Marco Selvi*, Cosmin Paduraru*, Edouard Leurent*, Shariq Iqbal, et al.
    Nature
    PDF Project Page Code BibTex

  6. MuZero, AlphaZero, and AlphaDev: Optimizing computer systems
    Google DeepMind blog
    Project Page

  7. Diversifying AI: Towards Creative Chess with AlphaZero
    Tom Zahavy, Vivek Veeriah, Shaobo Hou, Kevin Waugh, Matthew Lai, Edouard Leurent, Nenad Tomasev, Lisa Schut, Demis Hassabis, Satinder Singh
    PDF BibTex

  8. Optimizing Memory Mapping Using Deep Reinforcement Learning
    Pengming Wang, Mikita Sazanovich, Berkin Ilbeyi, Phitchaya Mangpo Phothilimthana, Manish Purohit, Han Yang Tay, Ngân Vũ, Miaosen Wang, Cosmin Paduraru, Edouard Leurent, Anton Zhernov, Julian Schrittwieser, Thomas Hubert, Robert Tung, Paula Kurylowicz, Kieran Milan, Oriol Vinyals, Daniel J. Mankowitz
    PDF BibTex

  9. RoboSoft
    Automated Planning for Robotic Guidewire Navigation in the Coronary Arteries
    Pierre Schegg, Jérémie Dequidt, Eulalie Coevoet, Edouard Leurent, Rémi Sabatier, Philippe Preux, Christian Duriez
    2022 IEEE 5th International Conference on Soft Robotics (RoboSoft), 2022
    PDF Video BibTex

  10. ALT
    Adaptive Reward-Free Exploration
    Emilie Kaufmann, Pierre Ménard, Omar Darwiche Domingues, Anders Jonsson, Edouard Leurent, Michal Valko
    International Conference on Algorithmic Learning Theory (ALT), 2021
    PDF Project Page Code BibTex

  11. Safe and Efficient Reinforcement Learning for Behavioural Planning in Autonomous Driving
    Edouard Leurent
    PhD Thesis
    PDF Slides BibTex
    ⭐⭐ awarded two prizes for best PhD thesis

  12. NeurIPS
    Robust-Adaptive Control of Linear Systems: beyond Quadratic Costs
    Edouard Leurent, Denis Efimov, Odalric-Ambrym Maillard
    Advances in Neural Information Processing Systems (NeurIPS), 2020, Vol. 33
    PDF Project Page Code Video Poster Slides BibTex
    Oral - 1.1% acceptance rate

  13. NeurIPS
    Planning in Markov Decision Processes with Gap-Dependent Sample Complexity
    Anders Jonsson, Emilie Kaufmann, Pierre Ménard, Omar Darwiche Domingues, Edouard Leurent, Michal Valko
    Advances in Neural Information Processing Systems (NeurIPS), 2020, Vol. 33
    PDF Project Page Code BibTex

  14. ALT
    Fast active learning for pure exploration in reinforcement learning
    Pierre Ménard, Omar Darwiche Domingues, Anders Jonsson, Emilie Kaufmann, Edouard Leurent, Michal Valko
    International Conference on Algorithmic Learning Theory (ALT), 2020
    PDF Project Page BibTex

  15. ACML
    Monte-Carlo Graph Search: the Value of Merging Similar States
    Edouard Leurent, Odalric-Ambrym Maillard
    Asian Conference on Machine Learning (ACML), 2020
    PDF Project Page Code BibTex

  16. CDC
    Robust-Adaptive Interval Predictive Control for Linear Uncertain Systems
    Edouard Leurent, Denis Efimov, Odalric-Ambrym Maillard
    Proceedings of the 59th Conference on Decision and Control (CDC 2020)
    PDF Video BibTex

  17. NeurIPS
    Budgeted Reinforcement Learning in Continuous State Space
    Nicolas Carrara*, Edouard Leurent*, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin
    Advances in Neural Information Processing Systems (NeurIPS), 2019, Vol. 32
    PDF Project Page Code Poster BibTex

  18. ML4AD @NeurIPS 2019
    Social Attention for Autonomous Decision-Making in Dense Traffic
    Edouard Leurent, Jean Mercat
    Machine Learning for Autonomous Driving Workshop at NeurIPS 2019
    PDF Project Page Code Poster BibTex

  19. CDC
    Interval Prediction for Continuous-Time Systems with Parametric Uncertainties
    Edouard Leurent, Denis Efimov, Tarek Raïssi, Wilfrid Perruquetti
    Conference on Decision and Control (CDC), 2019
    PDF Project Page Code Slides BibTex

  20. ECML-PKDD
    Practical Open-Loop Optimistic Planning
    Edouard Leurent, Odalric-Ambrym Maillard
    European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), 2019
    PDF Project Page Code Poster Slides BibTex

  21. MLITS @NeurIPS 2018
    Approximate Robust Control of Uncertain Dynamical Systems
    Edouard Leurent, Yann Blanco, Denis Efimov, Odalric-Ambrym Maillard
    Machine Learning for Intelligent Transportation System workshop at NeurIPS 2018
    PDF Project Page Code Video Poster BibTex

Projects

  1. Nature GO
    A wildlife identification game exploring the use of generative AI

  2. twitter-graph
    Fetch and visualize the graph of your Twitter friends

  3. Prescription
    Tool to determine the statute of limitations for sexual offences in French criminal law

  4. Highway Env
    A collection of environments for behavioral planning tasks in autonomous driving

  5. IGNite
    Generation of georeferenced maps from IGN services (France)

  6. Sisyphe
    Learn poetry by progressively hiding words

  7. Kestrel FPV
    Quadcopter FPV Racing simulator

  8. Mozaik
    Automatic reproduction of images with simple primitives

  9. Icarus
    Design and construction of a DIY quadcopter running on Arduino

  10. Spelling
    Spelling correction with a Naive Bayes classifier

  11. Melodic Dictation
    Signal processing tool to recover the music score from an audio file

  12. Hacktamine
    Coding battle webapp

  13. Students Website
    Website for the students of Mines ParisTech, powered by django

Accomplishments