Eugene Belilovsky

Associate Professor at Concordia University ⋅ Academic Member of Mila – Quebec AI Institute

Eugene Belilovsky

I am an Associate Professor at Concordia University and Mila since 2021. Previously, I was a Postdoctoral Researcher at Mila and the University of Montreal, working with Aaron Courville. I completed a joint PhD at CentraleSupélec, University of Paris-Saclay and KU Leuven (VISICS), supervised by Matthew Blaschko, in 2018. During my PhD I also visited the University of Toronto Machine Learning Group, working with Richard Zemel and Raquel Urtasun, and interned in the core machine learning groups at Apple (with Tomas Pfister) and Amazon (with Matthias Seeger).

Broadly, my research interests are in efficient training for large-scale deep learning. My current research focuses on emerging paradigms for the future of large-scale pre-training that will be continual (growing in tasks and modalities), decentralized in data (federated), and in communication (decentralized/distributed deep learning). I am also interested in a variety of applications of machine learning, particularly involving computer vision — ranging from specific problems in healthcare to scene understanding and 3D reasoning.

Affiliations

News

Feb 2026Two papers on meta-generalization with learned optimizers accepted at ICLR 2026, and our library PyLO is accepted at MLSys 2026! 🎉
2025I received tenure! Many thanks to our lab's students and collaborators. 🎓
Jan 2025Our group has 3 papers accepted at ICLR 2025.
Sep 2023Two papers accepted at NeurIPS 2023, on Federated Transfer Learning and Decentralized Learning.
2023Recipient of an FRQNT New Scholar grant and co-PI on two FRQNT team grants — thanks FRQNT for the support!
2023PhD students Benjamin Therien and Abhinav Moudgil received the FRQNT Doctoral Scholarship.
Apr 2023Our group has 3 papers accepted at ICML 2023.
2023Nasir Khalid, Nader Asadi, and Amir Sarfi successfully defended their MSc theses with a grade of outstanding.
Mar 2023Co-organizing the workshop on Localized Learning at ICML 2023.
Feb 2023Amir Sarfi's paper accepted at CVPR 2023.
Sep 2022CLIP-Mesh accepted at SIGGRAPH Asia 2022.