I am currently the head of the AI Unit at EffiSciences. I am a former graduate of the MVA Master's program at ENS Paris-Saclay.
I work on mainly on AI safety. I have organized and led the Turing Seminar, a course on AI safety in the MVA Master's program, and the bootcamps ML4Good. This site contains past student work. You can find here more recent work on AI safety, which focuses on RLHF and interpretability.
I was previously the CTO of Omnisciences, which is now defunct :). I've researched at Inria Parietal and Neurospin, and enjoy philosophy and jazz piano.
Here is my LinkedIn, Twitter, and Github profiles.
SinGAN is a generative model that can be learned from a single natural image. We propose a rigorous method to evaluate the image creation capabilities of a GAN using the PatchMatch algorithm.
The human brain combines top-down and bottom-up signals. Bottom-up signals result from direct perception, while top-down signals take into account past experience.

I worked on the Belief Propagation algorithm, and unified the notations between causal Bayesian graphs and factor graphs. Take the time to look at our report, which contains some very nice maths. We have also written a very versatile implementation of the belief propagation algorithm for factor graphs.

I’ve worked on the coherence of the nearest neighbor algorithm with the Bayesian axioms of probability. This project required the writing of highly optimized Numba routines.

In this repository, you will find my work done during the course of 3D computer vision. During the last TP, we reconstructed a face in 3D from two photos.

Here is a solution to the Inria-BCI competition. This solution would be ranked 4th in the original competition.
In this repository you will find an efficient implementation of the paper All resolution inference for brain imaging. This paper proposes a new methodology to construct brain statistics when using fMRI data.
In this repo, I apply the methodology of MEG signal analysis using the MNE library.

In this repository, you will find the winner’s solution of the KIRO2018, in partnership with Air France. We build in an iterative way a solution to the scheduling problem of the Air France aircraft fleet.

In this repository, you will find the winner’s solution of the extended competition of the KIRO2019. We efficiently built the graph of 5G antennas connected by optical fiber in major French cities.

In this paper written to validate the Biostatistics course, I critique/destroy the statistical methodology used by two highly cited papers written at the beginning of the Covid epidemic.

Boogie-Woogie is great fun to play on the piano, and it’s also pretty easy to automate.

In this essay, I use concepts from Gestalt psychology to describe the patterns of the birds of Escher and I play with the attention of the viewer. Gestalt psychology is in a way the ancestor of the interpretability of neural networks in vision processing.