Selected publications and recent work. For a comprehensive, up-to-date list, see my Google Scholar profile.
MLSys
PyLO: Towards Accessible Learned Optimizers in PyTorch
Paul Janson, Benjamin Therien, Quentin Anthony, Xiaolong Huang, Abhinav Moudgil, Eugene Belilovsky
MLSys 2026
arXiv
ICLR
μLO: Compute-Efficient Meta-Generalization of Learned Optimizers
Benjamin Thérien, Charles-Étienne Joseph, Boris Knyazev, Edouard Oyallon, Irina Rish, Eugene Belilovsky
ICLR 2026
arXiv
ICLR
Celo: Training Versatile Learned Optimizers on a Compute Diet
Abhinav Moudgil, Boris Knyazev, Guillaume Lajoie, Eugene Belilovsky
ICLR 2026
arXiv
ICML
DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone
Vaibhav Singh, Oleksiy Ostapenko, Pierre-André Noël, Eugene Belilovsky, Torsten Scholak
ICML 2026
arXiv
ICML
MuLoCo: Muon is a Practical Inner Optimizer for DiLoCo
Benjamin Thérien, Xiaolong Huang, Aaron Defazio, Irina Rish, Eugene Belilovsky
ICML 2026
arXiv
arXiv
Can Model Merging Improve Aggregation in DiLoCo?
Stefan Horoi, Benjamin Thérien, Guy Wolf, Eugene Belilovsky
Preprint
arXiv
arXiv
Unifying Local Communications and Local Updates for LLM Pretraining
Pietro Cagnasso, Eugene Belilovsky, Edouard Oyallon
Preprint
arXiv
arXiv
Learned Subspace Compression for Communication-Efficient Pipeline Parallelism (MAPL)
Paul Janson, Edouard Oyallon, Eugene Belilovsky
Preprint
arXiv
NeurIPS
ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training
Adel Nabli, Louis Fournier, Pierre Erbacher, Louis Serrano, Eugene Belilovsky, Edouard Oyallon
NeurIPS 2025
arXiv
arXiv
Overcoming the Communication-Performance Tradeoff in LLM Pretraining (SparseLoCo)
Amir Sarfi, Benjamin Thérien, Joel Lidin, Eugene Belilovsky
Preprint
arXiv
arXiv
Model Parallelism With Subnetwork Data Parallelism
Vaibhav Singh, Zafir Khalid, Pietro Cagnasso, Edouard Oyallon, Eugene Belilovsky
Preprint
arXiv
NeurIPS
Guiding the Last Layer in Federated Learning with Pre-Trained Models
Gwen Legate, Nicolas Bernier, Lucas Caccia, Edouard Oyallon, Eugene Belilovsky
NeurIPS 2023
arXiv
NeurIPS
A²CiD²: Accelerating Asynchronous Communication in Decentralized Deep Learning
Adel Nabli, Eugene Belilovsky, Edouard Oyallon
NeurIPS 2023
arXiv
CVPR
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
MohammadReza Davari, Nader Asadi, Sudhir Mudur, Rahaf Aljundi, Eugene Belilovsky
CVPR 2022
PDF
SIGGRAPH Asia
CLIP-Mesh: Generating Textured Meshes from Text Using Pretrained Image-Text Models
Nasir Khalid, Tianhao Xie, Eugene Belilovsky, Tiberiu Popa
SIGGRAPH Asia 2022
arXiv Project
ECCV
Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors
Mateusz Michalkiewicz, Sarah Parisot, Stavros Tsogkas, Mahsa Baktashmotlagh, Anders P. Eriksson, Eugene Belilovsky
ECCV 2020
PDF Code
ICML
Decoupled Greedy Learning of CNNs
Eugene Belilovsky, Michael Eickenberg, Edouard Oyallon
ICML 2020
arXiv Code
NeurIPS
Online Continual Learning with Maximally Inferred Retrieval
Rahaf Aljundi*, Lucas Caccia*, Eugene Belilovsky*, Massimo Caccia*, Min Lin, Laurent Charlin, Tinne Tuytelaars
NeurIPS 2019 · *equal contribution
arXiv Code
ICML
Greedy Layerwise Learning Can Scale to ImageNet
Eugene Belilovsky, Michael Eickenberg, Edouard Oyallon
ICML 2019
PDF Code
ICCV
Scaling the Scattering Transform: Deep Hybrid Networks
Edouard Oyallon, Eugene Belilovsky, Sergey Zagoruyko
ICCV 2017
PDF Code
ICML
Learning to Discover Sparse Graphical Model Structures
Eugene Belilovsky, Kyle Kastner, Gaël Varoquaux, Matthew B. Blaschko
ICML 2017
PDF Code
NeurIPS
Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity
Eugene Belilovsky, Gaël Varoquaux, Matthew B. Blaschko
NIPS 2016
PDF Code
ICLR
A Test of Relative Similarity for Model Selection in Generative Models
Eugene Belilovsky*, Wacha Bounliphone*, Matthew Blaschko, Ioannis Antonoglou, Arthur Gretton
ICLR 2016 · *equal contribution
PDF Code