About
I’m a PhD student at the University of Cambridge working (mostly) on Generative Modelling and Reinforcement Learning.
I completed the MVA master’s program (Mathématiques, Vision et Apprentissage) at Institut Polytechnique de Paris together with an engineering degree in applied mathematics and computer science at Télécom Paris. I was also fortunate to have worked with amazing researchers at Google DeepMind, EPFL and the Technology Innovation Institute.
I am usually open to collaborations on the topics listed below. Feel free to reach out via email if you want to work together on exciting projects.
Check my Google Scholar profile for an updated list of my publications.
Research interests
-
Discrete Diffusion Modeling
Masked and uniform-state diffusion on finite state spaces, diffusion language models, and semi-autoregressive block decoding.
-
Reinforcement Learning for Generative Models
Post-training LLMs and Diffusion Models with RL, Preference Optimization.
-
Continuous Diffusion Modeling & Neural Sampling
Sampling unnormalised densities with Diffusion Samplers, Stochastic Optimal Control.
-
High-Dimensional Statistics
Random Matrix Theory for Machine Learning, Exact asymptotics of learning when dimension and sample size row together.
Software
-
Scientific Reading
A local app to keep track of the papers read. Papers are organised by topic, and each one gets a TL;DR, a summary and notes written in LaTeX, edited side by side with the PDF.
-
Chatbot with API
A local API and chat interface to talk to LLMs downloaded with Ollama, so everything runs on your own machine.