avatar

Clément Romac

Research Scientist / Ph.D. Student
Hugging Face / Inria Bordeaux (France)
clement[dot]romac[at]gmail[dot]com


About Me

Hi, I am Clément Romac. I am Research Scientist at Hugging Face and a thrid-year PhD student jointly supervised by Pierre-Yves Oudeyer (FLOWERS team, Inria Bordeaux) and Thomas Wolf (Hugging Face) studying how curiosity-driven RL can help grounding Large Language Models.

Previously, I worked as a Machine Learning Engineer at Weenove and as a Research Engineer in the FLOWERS team working on Automatic Curriculum Learning for Deep RL and Automated scientific discovery in complex systems (e.g. self-organizing). I am also co-animating the Machine Learning Meetup group of Bordeaux.

Research Interests

News

Publications

  1. Loris Gaven, Thomas Carta, Clément Romac, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
    Preprint, 2024

  2. NAACL Findings
    Mohamed Salim Aissi, Clement Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, Olivier Sigaud, Laure Soulier, Nicolas Thome
    NAACL Findings 2025.

  3. IMOL Workshop
    Loris Gaven, Clément Romac, Thomas Carta, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
    IMOL Workshop, NeurIPS 2024.

  4. ARLET Workshop
    Quentin Gallouédec, Edward Beeching, Clément Romac, Emmanuel Dellandrea
    ARLET Workshop, ICML 2024.

  5. ICML
    Thomas Carta, Clément Romac, Thomas Wolf, Sylvain Lamprier, Olivier Sigaud, Pierre-Yves Oudeyer
    International Conference on Machine Learning (ICML), 2023.

  6. ICML
    Clément Romac, Rémy Portelas, Katja Hofmann, Pierre-Yves Oudeyer
    International Conference on Machine Learning (ICML), 2021.

  7. Rémy Portelas, Clément Romac, Katja Hofmann, Pierre-Yves Oudeyer
    Preprint, 2020


Projects

  1. ChatGPT explained in 5 minutes
    A series of short videos explaining Large Language Models.

  2. Lamorel
    Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).

  3. Automated Discovery Tool
    A software for assisted and automated discovery of patterns in the exploration of complex systems.

  4. Interactive Deep RL Demo
    In-browser interactive demo of Deep Reinforcement Learning agents' adaptation to unknown 2D tasks.

Other stuff


Powered by Jekyll and Minimal Light theme.