Mido Assran
RESEARCH SCIENTIST | MONTREAL, CANADA
Mido is a Research Scientist in Fundamental AI Research (FAIR). Previously, he obtained his PhD in Electrical and Computer Engineering from McGill University and Mila, the Quebec AI Institute. Mido's current research is focused on enabling computers to develop common sense perceptual models of our world for reasoning and planning in the physical world, specifically, through self-supervised learning from video. In the past, Mido has also worked on parallelizing deep reinforcement learning, and large-scale numerical optimization.
Research Areas
Mido's Work
Mido's Publications
June 11, 2025
RESEARCH
COMPUTER VISION
A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs
Benno Krojer, Mojtaba Komeili, Candace Ross, Koustuv Sinha, Mido Assran, Nicolas Ballas, Quentin Garrido
June 11, 2025
June 11, 2025
ROBOTICS
RESEARCH
V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
Mojtaba Komeili, Sarath Chandar, Abha Gejji, Ada Martin, Adrien Bardes, Ammar Rizvi, Artem Zholus, Claire Roberts, Daniel Dugas, David Fan, Francisco Massa, Francois Robert Hogan, Franziska Meier, Kapil Krishnakumar, Koustuv Sinha, Marc Szafraniec, Matthew Muckley, Mido Assran, Michael Rabbat, Nicolas Ballas, Patrick Labatut, Piotr Bojanowski, Quentin Garrido, Russell Howes, Sergio Arnaud, Vasil Khalidov, Xiaodong Ma, Yann LeCun, Yong Li
June 11, 2025
April 17, 2025
ROBOTICS
RESEARCH
Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D
Ruslan Partsey, Ayush Jain, Ang Cao, Ishita Prasad, Aravind Rajeswaran, Abha Gejji, Ada Martin, Arjun Majumdar, Daniel Dugas, Franziska Meier, Krishna Murthy Jatavallabhula, Mido Assran, Mikael Henaff, Mike Rabbat, Mrinal Kalakrishnan, Nicolas Ballas, Oleksandr Maksymets, Paul McVay, Phillip Thomas, Alexander Sax, Sergio Arnaud, Vincent-Pierre Berges
April 17, 2025
February 15, 2024
CORE MACHINE LEARNING
Revisiting Feature Prediction for Learning Visual Representations from Video
Nicolas Ballas, Adrien Bardes, Mido Assran, Michael Rabbat, Quentin Garrido, Xinlei Chen, Yann LeCun, Jean Ponce
February 15, 2024
June 18, 2023
CORE MACHINE LEARNING
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
Nicolas Ballas, Ishan Misra, Mido Assran, Mike Rabbat, Pascal Vincent, Piotr Bojanowski, Quentin Duval, Yann LeCun
June 18, 2023
September 16, 2020
Advances in Asynchronous Parallel and Distributed Optimization
Mike Rabbat, Mido Assran, Arda Aytekin, Hamid Feyzmahdavian, Mikael Johansson
September 16, 2020
Our approach
Latest news
Foundational models
Meta © 2026