Hugo Touvron

Hugo joined Facebook AI Research as a resident PhD student in November 2019. He is advised by Hervé Jégou (Facebook) and Matthieu Cord (Sorbonne University). Hugo holds two bachelor’s degree from École Polytechnique and Paris Dauphine University and three master’s degree in mathematics and computer science from École Polytechnique, ENS Paris-Saclay and ENSTA ParisTech. His research interests include image classification, transfer learning, fine-grained recognition and more generally: the application of transformers in computer vision.

Research Areas

Hugo's Publications

July 18, 2021

CORE MACHINE LEARNING

ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases

Convolutional architectures have proven extremely successful for vision tasks. Their hard inductive biases enable sample-efficient learning …

Stephane d’Ascoli, Hugo Touvron, Matthew L. Leavitt, Ari S. Morcos, Giulio Biroli, Levent Sagun

July 18, 2021