Mahmoud Assran

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 27

Top Topics

Asynchronous Cellular Automata

Visual Representations

Stochastic Gradient

Supervised Learning

Top Venues

Publications

Adrien Bardes, Quentin Garrido, Jean Ponce, Xinlei Chen, Michael G. Rabbat, Yann LeCun, Mahmoud Assran, Nicolas Ballas
Revisiting Feature Prediction for Learning Visual Representations from Video. CoRR (2024)
Duy-Kien Nguyen, Mahmoud Assran, Unnat Jain, Martin R. Oswald, Cees G. M. Snoek, Xinlei Chen
An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels. CoRR (2024)
Samuel Lavoie, Polina Kirichenko, Mark Ibrahim, Mahmoud Assran, Andrew Gordon Wilson, Aaron C. Courville, Nicolas Ballas
Modeling Caption Diversity in Contrastive Vision-Language Pretraining. CoRR (2024)
Quentin Garrido, Mahmoud Assran, Nicolas Ballas, Adrien Bardes, Laurent Najman, Yann LeCun
Learning and Leveraging World Models in Visual Representation Learning. CoRR (2024)
Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael G. Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jégou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski
DINOv2: Learning Robust Visual Features without Supervision. CoRR (2023)
Amir Bar, Florian Bordes, Assaf Shocher, Mahmoud Assran, Pascal Vincent, Nicolas Ballas, Trevor Darrell, Amir Globerson, Yann LeCun
Predicting masked tokens in stochastic locations improves masked image modeling. CoRR (2023)
Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Yann LeCun, Nicolas Ballas
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture. CoRR (2023)
Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Yann LeCun, Nicolas Ballas
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture. CVPR (2023)
Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Michael G. Rabbat, Nicolas Ballas
Masked Siamese Networks for Label-Efficient Learning. CoRR (2022)
Mahmoud Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Nicolas Ballas
The Hidden Uniform Cluster Prior in Self-Supervised Learning. CoRR (2022)
Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Florian Bordes, Pascal Vincent, Armand Joulin, Mike Rabbat, Nicolas Ballas
Masked Siamese Networks for Label-Efficient Learning. ECCV (31) (2022)
Paul-Aymeric McRae, Prasanna Parthasarathi, Mahmoud Assran, Sarath Chandar
Memory Augmented Optimizers for Deep Learning. CoRR (2021)
Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Armand Joulin, Nicolas Ballas, Michael G. Rabbat
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples. ICCV (2021)
Mahmoud Assran, Michael G. Rabbat
Asynchronous Gradient Push. IEEE Trans. Autom. Control. 66 (1) (2021)
Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Armand Joulin, Nicolas Ballas, Michael G. Rabbat
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples. CoRR (2021)
Mahmoud Assran, Arda Aytekin, Hamid Reza Feyzmahdavian, Mikael Johansson, Michael G. Rabbat
Advances in Asynchronous Parallel and Distributed Optimization. Proc. IEEE 108 (11) (2020)
Mahmoud Assran, Michael G. Rabbat
On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings. CoRR (2020)
Mahmoud Assran, Nicolas Ballas, Lluís Castrejón, Michael G. Rabbat
Recovering Petaflops in Contrastive Semi-Supervised Learning of Visual Representations. CoRR (2020)
Mahmoud Assran, Arda Aytekin, Hamid Reza Feyzmahdavian, Mikael Johansson, Michael G. Rabbat
Advances in Asynchronous Parallel and Distributed Optimization. CoRR (2020)
Shagun Sodhani, Olivier Delalleau, Mahmoud Assran, Koustuv Sinha, Nicolas Ballas, Michael G. Rabbat
A Closer Look at Codistillation for Distributed Training. CoRR (2020)
Mahmoud Assran, Mike Rabbat
On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings. ICML (2020)
Mahmoud Assran, Joshua Romoff, Nicolas Ballas, Joelle Pineau, Mike Rabbat
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning. CoRR (2019)
Mahmoud Assran, Nicolas Loizou, Nicolas Ballas, Michael G. Rabbat
Stochastic Gradient Push for Distributed Deep Learning. ICML (2019)
Mahmoud Assran, Joshua Romoff, Nicolas Ballas, Joelle Pineau, Mike Rabbat
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning. NeurIPS (2019)
Mahmoud Assran, Nicolas Loizou, Nicolas Ballas, Michael G. Rabbat
Stochastic Gradient Push for Distributed Deep Learning. CoRR (2018)
Mahmoud Assran, Michael G. Rabbat
Asynchronous Subgradient-Push. CoRR (2018)
Mahmoud Assran, Michael G. Rabbat
An empirical comparison of multi-agent optimization algorithms. GlobalSIP (2017)