Oumayma Bounou

profile.PNG

C409

Inria, 2 Rue Simone Iff

Paris, France

I’m a postdoctoral researcher at NYU, where I am working with Yann Lecun on world models. Before that, I completed my PhD in the WILLOW project-team which is a joint team between Inria Paris, the Department of Computer Science of Ecole Normale Supérieure, and CNRS, where I was advised by Justin Carpentier and Jean Ponce.
Prior to that, I received an engineering degree from Télécom Paris.

My research interests lie in world models, control and optimization.

news

Jan 2025 I joined Yann Lecun’s group at NYU as a postdoc!
Dec 2024 I was in Milan to present our work on Learning System Dynamics under Optimal Control Guidance at CDC 2024.
Oct 2024 I successfully defended my PhD!
Dec 2023 I was in Singapore to visit Eureka Robotics and to present our work on differentiating optimal control solvers at CDC 2023.
Jul 2023 Our work on differentiating optimal control solvers was accepted to CDC 2023!

publications

  1. Value-Guided Action Planning with JEPA World Models
    Matthieu Destrade, Oumayma Bounou, Quentin Le Lidec, Jean Ponce, and Yann LeCun
    arXiv preprint arXiv:2601.00844 2025
    PDF
  2. Closing the Train–Test Gap in World Models for Gradient-Based Planning
    Arjun Parthasarathy, Nimit Kalra, Rohun Agrawal, Yann LeCun, Oumayma Bounou, Pavel Izmailov, and Micah Goldblum
    arXiv preprint arXiv:2512.09929 2025
    PDF
  3. Learning System Dynamics from Sensory Input under Optimal Control Principles
    Oumayma Bounou, Jean Ponce, and Justin Carpentier
    In IEEE 63rd Conference on Decision and Control (CDC) Dec 2024
    PDF
  4. Leveraging Proximal Optimization for Differentiating Optimal Control Solvers
    Oumayma Bounou, Jean Ponce, and Justin Carpentier
    In IEEE 62nd Conference on Decision and Control (CDC) Dec 2023
    PDF
  5. Online Learning and Control of Complex Dynamical Systems from Sensory Input
    Oumayma Bounou, Jean Ponce, and Justin Carpentier
    In Thirty-Fifth Conference on Neural Information Processing Systems 2021
    PDF
  6. Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach
    Xi Shen, Ilaria Pastrolin, Oumayma Bounou, Spyros Gidaris, Marc Smith, Olivier Poncet, and Mathieu Aubry
    In 2020 25th International Conference on Pattern Recognition (ICPR) 2021
    PDF
  7. A Web Application for Watermark Recognition
    Oumayma Bounou, Tom Monnier, Ilaria Pastrolin, Xi SHEN, Christine Benevent, Marie-Françoise Limon-Bonnet, François Bougard, Mathieu Aubry, Marc H. Smith, Olivier Poncet, and Pierre-Guillaume Raverdy
    Journal of Data Mining and Digital Humanities Jul 2020
    PDF