PeopleofSuperintelligence

Researcher

Elliot Chane-Sane

Elliot Chane-Sane is a robotics researcher whose work connects reinforcement learning with embodied AI and language-model reasoning. He earned an engineering degree from École Polytechnique and a MASt in Mathematical Statistics at Cambridge, then completed a PhD with the Willow team at Inria Paris and École Normale Supérieure in 2023. His research includes imagined subgoals for reinforcement learning, video-conditioned robot manipulation and visual quadruped locomotion; he also coauthored Mistral's Magistral reasoning model in 2025. He contributes to Mistral AI's AI Science Robotics group on Robostral Navigate, an 8B robot-navigation model that uses a single RGB camera and plain-language instructions.

Links
Website, Google Scholar, LinkedIn and GitHub

Timeline

  1. 2020–2023

    Degrees and PhD in robot learning

    Before research, he earns an engineering degree at École Polytechnique and a MASt in Mathematical Statistics at the University of Cambridge. He begins a PhD in the Willow team at Inria Paris and École Normale Supérieure in October 2020, then graduates in September 2023 under Ivan Laptev and Cordelia Schmid. In 2021, he coauthors an ICML paper that uses imagined subgoals to train goal-conditioned reinforcement-learning policies.

  2. 2023

    Video instructions for robot manipulation

    He coauthors the 2023 ICRA paper Learning Video-Conditioned Policies for Unseen Manipulation Tasks, which uses human video demonstrations to guide robot manipulation on unseen tasks. The method shows zero-shot transfer without paired human instructions and robot trajectories.

  3. 2024

    SoloParkour on a quadruped

    He coauthors SoloParkour, a constrained reinforcement-learning method for visual quadruped locomotion. The team transfers a policy from privileged experience to depth-based control and demonstrates parkour skills on a real Solo-12 robot.

  4. 2024

    A LocoLearn workshop award

    He coauthors Reinforcement Learning from Wild Animal Videos, a project on legged-locomotion skills learned from internet animal videos. It receives the Best Paper Award at the 2024 CoRL LocoLearn Workshop.

  5. 2025

    Magistral reasoning model

    He coauthors the 2025 Magistral paper, which introduces Mistral AI's first reasoning model and a scalable reinforcement-learning pipeline.

  6. As of October 2026

    Robostral Navigate at Mistral

    He contributes to Mistral AI's AI Science Robotics group on Robostral Navigate, an 8B embodied-navigation model that takes a plain-language instruction and one RGB camera view. The model achieves 76.6% success on unseen R2R-CE benchmarks.

  1. Google had the most people shaping AI every year from 2014 to 2025Our estimates of which organizations employed the most people shaping AI from 1961 to 2025, with a year-by-year chart.
  2. The United States employs an estimated 53% of people in our data with a known employment countryOur estimates of where AI careers are concentrated now and how countries’ shares of dated positions changed over time.
  3. 46% of living people in our data with known birth and employment countries work outside their birth countryOur estimate of cross-border careers in AI, from country of birth and the country of each current organization.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionOur estimates of where the people shaping AI studied and where their careers led, from education records in cited biographies.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Elliot Chane-Sane yet. Send us a free-licensed photo.

  1. Elliot Chane-Sane elliotchanesane31.github.io. Checked 19 October 2026.
  2. WILLOW - 2023 - Rapport annuel d'activité rex-radar.inria.fr. Checked 19 October 2026.
  3. Goal-Conditioned Reinforcement Learning with Imagined Subgoals proceedings.mlr.press. Checked 19 October 2026.
  4. Learning Video-Conditioned Policies for Unseen Manipulation Tasks di.ens.fr. Checked 19 October 2026.
  5. SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience arxiv.org. Checked 19 October 2026.
  6. Magistral arxiv.org. Checked 19 October 2026.
  7. Robostral Navigate: single-camera AI navigation | Mistral AI mistral.ai. Checked 19 October 2026.