Eugene Belilovsky bio photo

Eugene Belilovsky

Researcher in Machine Learning

Email Twitter Github

I am an Assistant Professor at Concordia University and Mila since 2021. Previously, I was a Postdoctoral Researcher at the Mila and at the University of Montreal working with Aaron Courville. I completed a (joint) PhD at CentraleSupelec, 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 at Amazon (with Matthias Seeger).

Broadly my research interests are in Machine Learning and Computer Vision. My current research focuses on emerging paradigms for the future of very large scale deep learning systems that will be continual (growing in tasks, modalities), decentralized in data (federated), and computation (decentralized deep learning). I am also intrested in a variety of applications of machine learning particularly involving computer vision, this ranges from specific problems in healthcare, to scene understanding, and 3D reasoning.

Recent News:

  • 2 Papers accepted at NeurIPS 2023 on Federated Transfer Learning and Decentralized Learning.
  • I am recepient of an FRQNT New Scholar grant and co-PI on 2 FRQNT team grants, thanks FRQNT for the support!
  • 2 of our PhD students Benjamin Therien and Abhinav Moudgil have received the FRQNT Doctoral Scholarship
  • Our group has 3 papers accepted at ICML 2023
  • Nasir Khalid, Nader Asadi, and Amir Sarfi have succesfully defend their MS thesis with a grade of outstanding
  • I am co-organizing the workshop on “Localized Learning” at ICML 2023
  • MS Amir Sarfi has a paper accepted at CVPR 2023
  • ClipMesh is accepted at SIGGRAPH Asia 2022, see project page