Profile 👋

I’m a final-year master’s student at École des Ponts · IP Paris, majoring in applied math.
Currently enrolled in the MVA M2 program at ENS Paris-Saclay (Math, Learning, Vision).

I enjoy both theoretical and experimental arguments and my interests include:
Learning from experience (RL) and Learning representations.

My recent focuses have been:

• Pre-training (Apertus, ACL’26) and Distillation (Falcon)
• Transformer architecture (FOG at NIPS’25).
• Overthinking in Reasoning Language Models (Terminator at ICLR’26)
• Studying exploration in GRPO.

Recently, I joined Mistral AI’s science team to work on long horizon RL, supervised by Albert Jiang.

Between early 2025 to early 2026, I was a visiting student at MLO lab at EPFL, supervised Prof. Martin Jaggi. I was also part of the Swiss AI Initiative core LLM team, an open-source initiative between EPFL, ETH Zurich, and CSCS.

Previously, I did an internship at the theory/frontier team of TII (UAE) and was member of the Falcon LLM team.

🛎️ News 🛎️:

• [March 2026] Our paper on tackling overthinking in RLMs is finally out.
• [Nov 2025] Excited to present our poster on FOG at NeurIPS in Paris on November 25th.
• [Sept 2025] Apertus family of fully open LLMs is released!
• [Dec 2024] Falcon3 family of open models is out: distillation FTW!