Profile 👋

I’m a machine learning researcher working on reinforcement learning and language models.
I am graduating from ENPC and the MVA program at ENS Paris-Saclay, with interests spanning empirical and theoretical approaches to learning algorithms.

My recent research has focused on:

• RL / Formal reasoning (Leanstral)
• Overthinking in reasoning language models (Terminator at ICLR’26)
• Transformer architecture (FOG at NIPS’25)
• Pre-training (Apertus at ACL’26) and Distillation (Falcon) at scale

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

Between early 2025 and early 2026, I was a visiting student at MLO lab at EPFL, supervised by 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 a member of the Falcon LLM team.

🛎️ News 🛎️:

• [July 2026] Weights + tech report + SafeVerify + FLTEval are now public, following Leanstral 1.5 release.
• [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!