Scholar
Clément ROMAC
Google Scholar ID: L7YK6t0AAAAJ
Research Scientist at Hugging Face / Ph.D. student at Inria (Flowers team)
Citations & Impact
Citations
365
H-index
5
i10-index
4
Publications
13
Co-authors
15
list available
Resume
Academic Achievements
- Publications: 'WorldLLM: Improving LLMs' world modeling using curiosity-driven theory-making' (RLDM 2025), 'MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spaces' (ICML 2025), 'Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting' (NAACL Findings 2025); Awards: Not explicitly mentioned; Patents: Not explicitly mentioned; Projects: MAGELLAN, WorldLLM, etc.
Research Experience
- Work Experience: Previously 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; Research Projects: MAGELLAN, WorldLLM, etc.; Position: Research Scientist / PhD Student.
Education
- Degree: PhD; School: Inria Bordeaux; Supervisors: Pierre-Yves Oudeyer (FLOWERS team, Inria Bordeaux) and Thomas Wolf (Hugging Face); Time: Expected to graduate by the end of 2025; Major: Reinforcement learning, curiosity-driven learning, language grounding.
Background
- Research Interests: How curiosity-driven reinforcement learning (RL) can help ground Large Language Models (LLMs) through online interactions with an environment; Professional Field: Machine learning, reinforcement learning, automatic curriculum learning; Brief Introduction: Currently a Research Scientist at Hugging Face and a PhD student at Inria Bordeaux, focusing on how curiosity-driven RL can ground LLMs through online interactions.
Miscellany
- Personal Interests: Involved in various dissemination initiatives, particularly in education, such as co-leading the development of the 'ChatGPT explained in 5 minutes' series of videos used in French classrooms and embedded in official trainings for workers from all French ministries; Also co-organizer of the Machine Learning Meetup group in Bordeaux.
