Quentin Garrido

I’m Quentin Garrido, a Member of Technical Staff at AMI Labs in Paris, working broadly on Self-Supervised Learning and World Models.

My research focuses on learning representations and world models from natural data such as raw videos, with work spanning video self-supervised learning (V-JEPA, V-JEPA 2), latent action world models, and the emergence of physics understanding in video models. Earlier in my career I worked on the foundations of self-supervised learning and its applications to computer vision and natural sciences.

Before joining AMI Labs, I was a Research Scientist at FAIR at Meta. I obtained my PhD in computer science from FAIR at Meta and Université Gustave Eiffel in 2025, co-advised by Yann LeCun and Laurent Najman. I also hold a master’s degree from the Mathématiques, Vision, Apprentissage (MVA) program at École Normale Supérieure Paris-Saclay, as well as an engineering degree in computer science from ESIEE Paris.