• Hi there!



    My skills
    My background
    My projects
    My resume

  • I am Lead Research Scientist at Jasper AI

    I am leading the Image Research team at Jasper AI working on Generative AI tasks such as inpainting, super-resolution, controllable shadows, light harmonization, matting, depth and surface-normals estimation, and product photograhpy in general.

  • Ph.D in Statistical Physics & Machine Learning Theory



    I completed my doctorate at IPhT (CEA Saclay) and ENS Paris late 2020, under the supervision of Lenka Zdeborová and Florent Krzakala. My research focused on the statistical physics of disordered systems, information theory, statistical inference and message-passing algorithms and their applications to theoretical machine learning (neural networks, phase retrieval, compressed sensing, matrix factorization,...).

    Read more about my research in my PhD thesis

    View my research projects

  • I interned in 2020 at Facebook Artificial Intelligence Research

    I contributed to a novel research direction at Facebook AI Research (FAIR) focused on robust machine learning, collaborating with renowned researchers Léon Bottou and David Lopez-Paz.

    Our research tackled a fundamental challenge in machine learning: developing algorithms that can identify and leverage truly causal features while ignoring spurious correlations. This work aimed to improve out-of-distribution generalization, a critical requirement for deploying robust AI systems in real-world applications.

    A key contribution was the development of six carefully designed linear unit tests that serve as benchmarks for evaluating out-of-distribution generalization capabilities. These tests, detailed in our published research, have become valuable tools for assessing and comparing different approaches to invariant feature learning. We released the code of the unit tests on Github.

Who am I?

I am currently Lead Research Scientist at Jasper AI (since 2024), where I lead the Image Research team. Previously, I was Research Scientist at Stability AI (2023) and was the first employee and Lead Research Scientist at Clipdrop (2021-2023), where I developed state-of-the-art computer vision models.

I obtained my Ph.D from Institut de Physique Théorique (IPhT - CEA Saclay, Université Paris-Saclay). Prior to this, I obtained a Master of Science in Theoretical physics at Ecole Normale Supérieure de Paris and a Master of Science and Engineering from Ecole polytechnique. I obtained as well a Bachelor of Science from Ecole polytechnique and was student in Classe Préparatoire aux Grandes Ecoles at Lycee Henri IV in Paris.

I was interested in statistical physics of disordered systems and I worked during my Ph.D with Lenka Zdeborová and Florent Krzakala on the application of these methods to provide a theoretical understanding of deep neural networks and more classical machine learning models and algorithms.

I interned in 2020 at Facebook Artificial Intelligence Research, where I worked with Léon Bottou and David Lopez-Paz on the development of linear unit tests for invariant feature learning.

Nowadays, I am interested in Generative AI and I am leading the Image Research team at Jasper AI (since 2024), where I work on Generative AI tasks such as inpainting, super-resolution, controllable shadows, light harmonization, matting, depth and surface-normals estimation, and product photograhpy in general.

In my spare time, I'm passionate about sports including indoor and outdoor skydiving, kitesurfing, windsurfing, surfing 🏄, hiking, biking 🚵‍♂️ and more!

Research projects

Controllable Shadow Generation with Single-Step Diffusion Models from Synthetic Data

Under review Dec, 2024

Style-Rank: Benchmarking stylization for diffusion models

Oct, 2024 Open-source

Flash Diffusion - Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

AAAI 2025 June, 2024

Linear unit-tests for invariance discovery

NeurIPS 2020 workshop - Causal Discovery & Causality-Inspired Machine Learning February 22, 2021

Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization

NeurIPS 2020 June 12, 2020

Tree-AMP: Compositional inference with tree approximate message passing

Journal of Machine Learning Research

Rademacher complexity and spin glasses: A link between the replica and statistical theories of learning

MSML 2020 December 5, 2019

Exact asymptotics for phase retrieval and compressed sensing with random generative priors

MSML 2020 September 14, 2019

The spiked matrix model with generative priors

NeurIPS 2019 June 1, 2019

Storage capacity of binary symmetric perceptrons

Journal of Physics A: Mathematical and Theoretical Janvier 2, 2019

The committee machine: Computational to statistical gaps in learning a two-layers neural network

NeurIPS 2018 June 14, 2018

Personal projects

A simple webservice and mobile app for Natural Language Understanding

NLU, frontend web and app

Background removal service

Matting with a trimap

Summary of my skills

Statistical physics

90%

Python, Matlab

90%

Compute vision, Diffusion models, Generative AI, Deep learning theory

90%

PyTorch, Pytorch-Lightning, DVC, Scikit-Learn, numpy, pandas, diffusers, transformers, ...

90%

MLOps, Bash, Git, Docker, Knative, Kubernetes, GCP, AWS

80%

HTML5, CSS3, JS, PHP, SQL

60%

React, ReactNative

70%

Java, C++, Rust, Julia

20%

Education

Statistical physics of disordered systems, Constraints statisfaction problems, Machine Learning, Deep Learning
Paris-Saclay University logo
Statistical physics, Numerical physics, Bayesian inference, Statistical field theory, Condensed matter, Non-linear physics, Stochastic processes, Non-equlibirum physics
ENS Paris-Saclay logo
Advanced quantum mechanics, Statistical physics, Computer science (advanced programming and algorithms), Probability, Statistics, Massive data processing, Control dynamic models,Fluid mechanics, Continuum mechanics, Particle physics, Soft mmatter, Complex systems, Quantum optics.
Ecole Polytechnique logo
Mathematics, Physics, Chemistry, Litterature, Foreign languages
Lycée Henri IV logo

Work Experience

Lead Research Scientist, Jasper AI February 2023 - Present

Lead 3+ research scientists on the development of the next generation of AI image editing models for marketing purposes.

Research Scientist, Stability AI March 2023 - February 2024

Research Scientist, working on inpainting models (Uncrop, Replace-background, Swap, Generative-fill, ...)

Lead Machine Learning Scientist, ClipDrop March 2021 - March 2023

Lead machine learning scientist @ ClipDrop, computer vision deep models for matting, inpainting, super-resolution, depth and surface-normals estimation, relight, ...

Facebook Artificial Intelligence Research March - December 2020

As suggested by the formulation "most cows appear in grass and most camels appear in sand", Empirical Risk Minimization relies essentially on the dominant background color pixels to produce a prediction. To address this issue, the idea is to learn invariant features across multiple training distributions and to use those correlations as a proxy for out-of distribution generalization. To clarify the situation, as a core project we started to design simple, memory cheap, linear 'unit-test' that already capture OoD generalization failures. We designed and proposed three linear problems (with three scrambled versions) that contain invariant causal correlations that we would like to learn, as well as a spurious correlation that we would like to discard.

Ph.D, Université Paris-Saclay October 2017 - December 2020

I established the phase diagrams of various machine learning models, using the replica method and message passing algorithms from statistical physics of disordered systems, with an emphasis on the potential differences between statistical and algorithmic thresholds, for simple synthetic and theoretically tractable tasks.

Research Internship, Massachusetts Institute of Technology (MIT) April 2016 - August 2016

Yves Couder, Emmanuel Fort and coworkers recently discovered that a millimetric droplet sustained on the surface of a vibrating fluid bath may self-propel through a resonant interaction with its own wave field. This internship within the department of Mathematics, aimed to study such a droplet, called a walker, crossing a submerged obstacle. This difference of depth, due to the obstacle, is analog to a changement of media and optical index in optics and thus we showed a Snell-Descartes law for walking droplets.

Research project, Université Paris-Sud, Laboratoire de Physique des Solides April 2016 - August 2016

The advent of graphene and topological insulators in 2005 and 2006 was a revolution in condensed matter physics. The main specificity of these two-dimensional materials have probed some theories established in very remote contexts in condensed matter, such as quantum mechanics and relativistic field theory, rather encountered in high-energy physics. It is about understanding the appearance of topological band structures in two-dimensional materials, semiconductors or semi-metal, covered by models called " strong bonds " and the study of electrical and thermal transport properties these particular materials by means of statistical physics .

Research internship, Thales Research and Technology April 2016 - August 2016

I was responsible of developing a measuring bench of the influence of external disturbances including sensitivity to mechanical vibration of new optoelectronic oscilateurs (OEO), which allow the generation of signals with very low noise for radar applications.