Author

Mahmoud Assran

Author of 3 papers in this index, working on world models and foundation models & pretraining.

3papers in this index

—career papers

—citations

—h-index

Identified by Semantic Scholar author 38698856 on the paper records, so a namesake does not share this page. Career figures are that profile's and are not on file yet.

Papers in this index

2025-02-17

Intuitive physics understanding emerges from self-supervised pretraining on natural videos

Quentin Garrido, Nicolas Ballas, Mahmoud Assran +5 · 71 citations

World models Foundation models & pretraining

2024-02-15

Revisiting Feature Prediction for Learning Visual Representations from Video

Adrien Bardes, Quentin Garrido, Jean Ponce +5 · 463 citations

Trans. Mach. Learn. Res.World models

2023-04-14

DINOv2: Learning Robust Visual Features without Supervision

Maxime Oquab, Timothée Darcet, Théo Moutakanni +23 · 10,015 citations

Trans. Mach. Learn. Res.Foundation models & pretraining

Works with

Nicolas Ballas Michael Rabbat Quentin Garrido Adrien Bardes Yann LeCunLaurent NajmanEmmanuel DupouxJean PonceXinlei ChenMaxime Oquab

Co-authors on the papers above, most frequent first. Linked names have a page here.

Works on

World models Foundation models & pretraining Video & generative modeling