Sotabase

Career

· Researcher at Stanford Security Lab, Stanford University2024–
· Applied Signal Technology
· Professor, McGill University
· Research Scientist, Meta
· Motorola

Publications (41)

DINOv2: Learning Robust Visual Features without Supervision
Trans. Mach. Learn. Res. · 2023
6,333
cited
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
arXiv.org · 2018
984
cited
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
Computer Vision and Pattern Recognition · 2023
615
cited
TarMAC: Targeted Multi-Agent Communication
International Conference on Machine Learning · 2018
465
cited
fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning.
Radiology: Artificial Intelligence · 2020
446
cited
Federated Learning with Buffered Asynchronous Aggregation
International Conference on Artificial Intelligence and Statistics · 2021
408
cited
Stochastic Gradient Push for Distributed Deep Learning
International Conference on Machine Learning · 2018
386
cited
Masked Siamese Networks for Label-Efficient Learning
European Conference on Computer Vision · 2022
382
cited
Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
Magnetic Resonance in Medicine · 2020
227
cited
SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
International Conference on Learning Representations · 2019
217
cited
Federated Learning with Partial Model Personalization
International Conference on Machine Learning · 2022
208
cited
Revisiting Feature Prediction for Learning Visual Representations from Video
Trans. Mach. Learn. Res. · 2024
190
cited
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples
IEEE International Conference on Computer Vision · 2021
166
cited
Papaya: Practical, Private, and Scalable Federated Learning
Conference on Machine Learning and Systems · 2021
156
cited
Using Deep Learning to Accelerate Knee MRI at 3T: Results of an Interchangeability Study.
AJR. American journal of roentgenology · 2020
114
cited
Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning
International Conference on Learning Representations · 2022
94
cited
On the Convergence of Nesterov's Accelerated Gradient Method in Stochastic Settings
International Conference on Machine Learning · 2020
69
cited
The Hidden Uniform Cluster Prior in Self-Supervised Learning
International Conference on Learning Representations · 2022
62
cited
Where to Begin? Exploring the Impact of Pre-Training and Initialization in Federated Learning
arXiv.org · 2022
45
cited
Benchmarking Neural Network Training Algorithms
arXiv.org · 2023
44
cited
Sotabase
Mike Rabbat | Researcher Profile | Sotabase | Sotabase