Current Research
I hold a researcher position at Criteo AI Lab. Previously, I obtained my PhD at Sorbonne Université, in the MLIA team of the LIP6 and ISIR laboratories, under the direction of Sylvain Lamprier and Patrick Gallinari. Since then, with the help of my PhD students and collaborators, my academic research has been focused on advancing the fundamentals of generative AI and applying them to different domains.
A complete list of my publications may be found here. Some of my recent research interests are highlighted below:
- theoretical understanding of generative models, notably GANs and diffusion;
- methodological advances of generative models, e.g. consistency models;
- fairness in generative AI;
- automatic 3D modeling and 3D generative models;
- video prediction and generation.
Previous Research Experience
I began my research career during my studies at Ecole Normale Supérieure de Lyon. In their first half, I discovered the research areas of formal proof systems and computer graphics. In their second half, I became interested in machine leaning and artificial intelligence, leading to my future PhD topic. I worked more particularly on:
- fairness and accountability of automated decision-making processes;
- robustness of classifiers to adversarial and random examples;
- convex optimization;
- unsupervised representation learning for time series.
Here is a list of my research internships (in reverse chronological order), that were done within the scope of my studies at Ecole Normale Supérieure de Lyon:
- EPFL, MLO laboratory, Lausanne, Switzerland, supervised by Martin Jaggi (5 months): unsupervised general purpose scalable representation learning for time series;
- ENS de Lyon, LIP laboratory, team MC2, Lyon, France, supervised by Omar Fawzi (6 months): robustness of classifiers to random and adversarial perturbations, convex optimization;
- Inria, team Privatics, Lyon, France, supervised by Daniel Le Métayer: fairness and accountability of automated decision-making processes;
- University of Konstanz, Computer Graphics and Media Informatics working group, Konstanz, Germany, supervised by Abdalla G. M. Ahmed and Oliver Deussen: blue-noise sampling;
- Inria, team Marelle, Valbonne, France, supervised by Yves Bertot: integration of a logical system in the higher order proof system Coq.