SAIL Montreal

What is SAIL Montreal?

SAIL Montreal (SAIT AI Lab Montreal) is a recently established academic-style research lab (in close collaboration with Mila) from Samsung whose mission is to advance our fundamental understanding of deep learning technology and its applications. Headed by Simon Lacoste-Julien, professor in computer science at Université de Montréal and co-founding member of Mila, SAIL is located in Mila's corporate space at the heart of the Montreal AI ecosystem nearby Borealis AI, FAIR, Microsoft Research and others where an open collaborative environment is encouraged.

Code: GitHub — Hugging Face

SAIL published papers (80)

* denotes equal contribution.

On the Sample Efficiency of Inverse Dynamics Models for Semi-Supervised Imitation Learning ICML 2026 Sacha Morin, Moonsub Byeon, Alexia Jolicoeur-Martineau, Sébastien Lachapelle
From Lyapunov Analysis to Algorithm Design in two-sided PL Minimax Optimization ICML 2026 Mansi Rankawat, Michael Muehlebach, Simon Lacoste-Julien, Damien Scieur
Convergence of Steepest Descent and Adam under Non-Uniform Smoothness ICML 2026 Sharan Vaswani, Yifan Sun, Reza Babanezhad
Towards Parameter-Free Temporal Difference Learning ICML 2026 Yunxiang LI, Mark Schmidt, Reza Babanezhad, Sharan Vaswani
Celo2: Towards Learned Optimization Free Lunch ICLR 2026 Abhinav Moudgil, Boris Knyazev, Eugene Belilovsky

Show all 80 papers Collapse the list

µLO: Compute-Efficient Meta-Generalization of Learned Optimizers ICLR 2026 Benjamin Thérien, Charles-Étienne Joseph, Boris Knyazev, Edouard Oyallon, Irina Rish, Eugene Belilovsky
Strongly Convex Sets in Riemannian Manifolds ICLR 2026 Damien Scieur, David Martínez-Rubio, Thomas Kerdreux, Alexandre d'Aspremont, Sebastian Pokutta
Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies JMLR — May 2026 Sébastien Lachapelle, Pau Rodriguez Lopez, Yash Sharma, Katie Everett, Rémi Le Priol, Alexandre Lacoste, Simon Lacoste-Julien
Identifiability of potentially degenerate Gaussian Mixture Models with piecewise affine mixing AISTATS 2026 Danru Xu, Sébastien Lachapelle, Sara Magliacane
Any-Property-Conditional Molecule Generation with Self-Criticism using Spanning Trees TMLR — Dec 2025 Alexia Jolicoeur-Martineau, Aristide Baratin, Kisoo Kwon, Boris Knyazev, Yan Zhang
(Almost) Free Modality Stitching of Foundation Models EMNLP 2025 Jaisidh Singh, Diganta Misra, Boris Knyazev, Antonio Orvieto
CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics EMNLP 2025 Shravan Nayak, Mehar Bhatia, Xiaofeng Zhang, Verena Rieser, Lisa Anne Hendricks, Sjoerd van Steenkiste, Yash Goyal, Karolina Stanczak, Aishwarya Agrawal
Learning Versatile Optimizers on a Compute Diet TMLR — Jun 2025 Abhinav Moudgil, Boris Knyazev, Guillaume Lajoie, Eugene Belilovsky
Ctrl-V: Higher Fidelity Autonomous Vehicle Video Generation with Bounding-Box Controlled Object Motion TMLR — May 2025 Ge Ya Luo, ZhiHao Luo, Anthony Gosselin, Alexia Jolicoeur-Martineau, Christopher Pal
Accelerating Training with Neuron Interaction and Nowcasting Networks ICLR 2025 Boris Knyazev, Abhinav Moudgil, Guillaume Lajoie, Eugene Belilovsky, Simon Lacoste-Julien
Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality ICLR 2025 Ge Ya Luo, Gian Mario Favero, ZhiHao Luo, Alexia Jolicoeur-Martineau, Christopher Pal
Interaction Asymmetry: A General Principle for Learning Composable Abstractions ICLR 2025 Jack Brady, Julius von Kügelgen, Sébastien Lachapelle, Simon Buchholz, Thomas Kipf, Wieland Brendel
Improving Equivariant Networks with Probabilistic Symmetry Breaking ICLR 2025 Hannah Lawrence, Vasco Portilheiro, Yan Zhang, Sékou-Oumar Kaba
(Accelerated) Noise-adaptive Stochastic Heavy-Ball Momentum TMLR — Apr 2025 Anh Dang, Reza Babanezhad, Sharan Vaswani
All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling AISTATS 2025 Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald, Luigi Gresele
Fast Convergence of Softmax Policy Mirror Ascent for Bandits & Tabular MDPs AISTATS 2025 Reza Asad, Reza Babanezhad, Issam H. Laradji, Nicolas Le Roux, Sharan Vaswani
Meta-learning Optimizers for Communication-Efficient Learning TMLR — Mar 2025 Charles-Étienne Joseph, Benjamin Thérien, Abhinav Moudgil, Boris Knyazev, Eugene Belilovsky
Maxwell's Demon at Work: Efficient Pruning by Leveraging Saturation of Neurons TMLR — Feb 2025 Simon Dufort-Labbé, Pierluca D'Oro, Evgenii Nikishin, Irina Rish, Pierre-Luc Bacon, Razvan Pascanu, Aristide Baratin
Understanding Adam Requires Better Rotation Dependent Assumptions NeurIPS 2025 Tianyue H. Zhang, Lucas Maes, Alan Milligan, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Damien Scieur, Simon Lacoste-Julien, Charles Guille-Escuret
Manifold Metric: A Loss Landscape Approach for Predicting Model Performance CoLLAs 2025 Pranshu Malviya, Jerry Huang, Aristide Baratin, Quentin Fournier, Sarath Chandar
Improved Generalization of Weight Space Networks via Augmentations ICML 2024 Aviv Shamsian, Aviv Navon, David W. Zhang, Yan Zhang, Ethan Fetaya, Gal Chechik, Haggai Maron
Unsupervised Concept Discovery Mitigates Spurious Correlations ICML 2024 Md Rifat Arefin, Yan Zhang, Aristide Baratin, Francesco Locatello, Irina Rish, Dianbo Liu, Kenji Kawaguchi
A Sparsity Principle for Partially Observable Causal Representation ICML 2024 Danru Xu, Dingling Yao, Sébastien Lachapelle, Perouz Taslakian, Julius von Kügelgen, Francesco Locatello, Sara Magliacane
Lookbehind-Sam: k steps back, 1 step forward ICML 2024 Goncalo Mordido, Pranshu Malviya, Aristide Baratin, Sarath Chandar
LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging ICML 2024 Jinuk Kim, Marwa El Halabi, Mingi Ji, Hyun Oh Song
Promoting Exploration in Memory-Augmented Adam using Critical Momenta TMLR — Jun 2024 Pranshu Malviya, Goncalo Mordido, Aristide Baratin, Reza Babanezhad, Jerry Huang, Simon Lacoste-Julien, Razvan Pascanu, Sarath Chanda
PopulAtion Parameter Averaging (PAPA) TMLR — May 2024 Alexia Jolicoeur-Martineau, Emy Gervais, Kilian FATRAS, Yan Zhang, Simon Lacoste-Julien
Graph Neural Networks for Learning Equivariant Representations of Neural Networks ICLR 2024 Miltiadis Kofinas, Boris Knyazev, Yan Zhang, Yunlu Chen, Gertjan J. Burghouts, Efstratios Gavves, Cees G. M. Snoek, David W. Zhang
How connectivity structure shapes rich and lazy learning in neural circuits ICLR 2024 Yuhan Helena Liu, Aristide Baratin, Jonathan Cornford, Stefan Mihalas, Eric Todd SheaBrown, Guillaume Lajoie
Object centric architectures enable efficient causal representation learning ICLR 2024 Amin Mansouri, Jason Hartford, Yan Zhang, Yoshua Bengio
Multi-View Causal Representation Learning with Partial Observability ICLR 2024 Dingling Yao, Danru Xu, Sébastien Lachapelle, Sara Magliacane, Perouz Taslakian, Georg Martius, Julius von Kügelgen, Francesco Locatello
Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees AISTATS 2024 Alexia Jolicoeur-Martineau, Kilian Fatras, Tal Kachman
Fairness in Submodular Maximization over a Matroid Constraint AISTATS 2024 Marwa El Halabi, Jakub Tarnawski, Ashkan Norouzi-Fard, Thuy-Duong Vuong
Adaptive Quasi-Newton and Anderson Acceleration Framework with Explicit Global (Accelerated) Convergence Rates AISTATS 2024 Damien Scieur
Iterative Methods via Locally Evolving Set Process NeurIPS 2024 Baojian Zhou, Yifan Sun, Xingzhi Guo, Deqing Yang, Yanghua Xiao, Reza Babanezhad
Bias in Motion: Theoretical Insights into the Dynamics of Bias and Robustness in SGD Training NeurIPS 2024 Anchit Jain, Rozhin Nobahari, Aristide Baratin, Stefano Sarao Mannelli
Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods TMLR — Nov 2023 Yuchen Liu, Zhen Liu, Aristide Baratin, Romain Laroche, Aaron Courville, Alessandro Sordoni
Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models? ICML 2023 Boris Knyazev, Doha Hwang, Simon Lacoste-Julien
Difference of submodular minimization via DC programming ICML 2023 Marwa El Halabi, George Orfanides, Tim Hoheisel
Fairness in Streaming Submodular Maximization over a Matroid Constraint ICML 2023 Marwa El Halabi*, Ashkan Norouzi-Fard*, Jakab Tardos*, Jakub Tarnawski*, Federico Fusco*
Unlocking Slot Attention by Changing Optimal Transport Costs ICML 2023 Yan Zhang*, David W Zhang*, Simon Lacoste-Julien, Gertjan J Burghouts, Cees GM Snoek
Equivariance with Learned Canonicalization Functions ICML 2023 Sékou-Oumar Kaba*, Arnab Kumar Mondal*, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh
CrossSplit: Mitigating Label Noise Memorization through Data Splitting ICML 2023 Jihye Kim, Aristide Baratin, Yan Zhang, Simon Lacoste-Julien
Fast Online Node Labelling with Local and Global Consistency ICML 2023 Baojian Zhou, Yifan Sun, Reza Babanezhad
Target-based Surrogates for Stochastic Optimization ICML 2023 J. Wilder Lavington, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Nicolas Le Roux
MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Learning EACL 2023 Oscar Manas, Pau Rodríguez*, Saba Ahmadi*, Aida Nematzadeh, Yash Goyal, Aishwarya Agrawal
Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees NeurIPS 2023 Sharan Vaswani, Amirreza Kazemi, Reza Babanezhad, Nicolas Le Roux
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation NeurIPS 2023 Sébastien Lachapelle, Divyat Mahajan, Ioannis Mitliagkas, Simon Lacoste-Julien
Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty TMLR — Dec 2022 Thomas George, Guillaume Lajoie, Aristide Baratin
SVRG meets AdaGrad: Painless Variance Reduction Machine Learning — Nov 2022 Benjamin Dubois-Taine, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Simon Lacoste-Julien
Towards Painless Policy Optimization for Constrained MDPs UAI 2022 Arushi Jain, Sharan Vaswani, Reza Babanezhad, Csaba Szepesvari, Doina Precup
Only tails matter: Average-Case Universality and Robustness in the Convex Regime ICML 2022 Leonardo Cunha, Gauthier Gidel, Fabian Pedregosa, Courtney Paquette, Damien Scieur
Towards Noise-adaptive, Problem-adaptive (Accelerated) SGD ICML 2022 Sharan Vaswani, Benjamin Dubois-Taine, Reza Babanezhad
Image Retrieval from Contextual Descriptions ACL 2022 Benno Krojer, Vaibhav Adlakha, Vibhav Vineet, Yash Goyal, Edoardo Ponti, Siva Reddy
On Evaluation Metrics for Graph Generative Models ICLR 2022 Rylee Thompson, Boris Knyazev, Elahe Ghalebi, Jungtaek Kim, Graham W. Taylor
Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation ICLR 2022 David W. Zhang*, Yan Zhang*, Gertjan J. Burghouts, Cees G. M. Snoek, Simon Lacoste-Julien
Super-Acceleration with Cyclical Step-sizes AISTATS 2022 Baptiste Goujaud, Damien Scieur, Aymeric Dieuleveut, Adrien Taylor, Fabian Pedregosa
Nonlinear acceleration of momentum and primal-dual algorithms Mathematical Programming — Feb 2022 Raghu Bollapragada, Damien Scieur, Alexandre d’Aspremont
The Curse of Unrolling: Rate of Differentiating Through Optimization NeurIPS 2022 Damien Scieur, Quentin Bertrand, Gauthier Gidel and Fabian Pedregosa
Data-Efficient Structured Pruning via Submodular Optimization NeurIPS 2022 Marwa El Halabi, Suraj Srinivas, Simon Lacoste-Julien
Hyper-Representations as Generative Models: Sampling Unseen Neural NetworkWeights NeurIPS 2022 Konstantin Schürholt, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth
MCVD: Masked Conditional Video Diffusion for Prediction NeurIPS 2022 Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal
Model Zoos: A Dataset of Diverse Populations of Neural Network Models NeurIPS 2022 Konstantin Schürholt, Diyar Taskiran, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth
Acceleration Methods Foundations and Trends in Optimization — Dec 2021 Alexandre d'Apresmont, Damien Scieur, Adrien Taylor
Infinite-Dimensional Optimization for Zero-Sum Games via Variational Transport ICML 2021 · Lewis Liu, Yufeng Zhang, Zhuoran Yang, Reza Babanezhad, Zhaoran Wang
Connecting Sphere Manifolds Hierarchically for Regularization ICML 2021 Damien Scieur, Youngsung kim
Affine Invariant Analysis of Frank-Wolfe on Strongly Convex Sets ICML 2021 Thomas Kerdreux, Lewis Liu, Simon Lacoste-Julien, Damien Scieur
Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning ICLR 2021 Namyeong Kwon, Hwidong Na, Gabriel Huang, Simon Lacoste-Julien
Average-case Acceleration for Bilinear Games and Normal Matrices ICLR 2021 Carles Domingo-Enrich, Fabian Pedregosa, Damien Scieur
An Analysis of the Adaptation Speed of Causal Models AISTATS 2021 Remi Le Priol, Reza Babanezhad, Yoshua Bengio, Simon Lacoste-Julien
Generalization of Quasi-Newton Methods: Application to Robust Symmetric Multisecant Updates AISTATS 2021 Damien Scieur, Lewis Liu, Thomas Pumir, Nicolas Boumal
Extra-gradient with player sampling for provable fast convergence in n-player games ICML 2020 Samy Jelassi, Carles Domingo Enrich, Damien Scieur, Arthur Mensch, Joan Bruna
Universal Average-Case Optimality of Polyak Momentum ICML 2020 Damien Scieur, Fabian Pedregosa
Average-case Acceleration Through Spectral Density Estimation ICML 2020 Fabian Pedregosa, Damien Scieur
Accelerating Smooth Games by Manipulating Spectral Shapes AISTATS 2020 Waïss Azizian, Damien Scieur, Ioannis Mitliagkas, Simon Lacoste-Julien, Gauthier Gidel

People

VP, Lab Director

Simon Lacoste-Julien

Website Scholar

Research Scientists

Damien Scieur

Website Scholar

Reza Babanezhad

Website Scholar

Yan Zhang

Website Scholar

Aristide Baratin

Website Scholar

Office Manager

Geneviève Bernard

Samsung Visiting Researchers

Moonsub Byeon

2025–26

Scholar

Kisoo Kwon

2024–25

Scholar

Jaewoo Lee

2024–25

Scholar

Kiho Cho

2023–24

Scholar

Eunhee Kang

2022–23

Scholar

Ji-Hye Kim

2022

Scholar

Doha Hwang

2021–22

Scholar

Hwidong Na

2020

Website

Namyeong Kwon

2020

Scholar

DoKwan Oh

2019–20

Scholar

Daehyun Ji

2019–20

Scholar

Alumni Research Scientists

Yash Goyal

2020–2025

Website Scholar

Marwa El Halabi

2020–2025

Website Scholar

Boris Knyazev

2022–2026

Website Scholar

Sébastien Lachapelle

2023–2026

Website Scholar

Presenting SAIL Montreal (ICML 2020)

SAIT AI Lab Montreal inauguration 2019

Samsung Electronics Expands SAIT AI Lab Montreal to Spur AI Research for Next-Generation System Semiconductor

Samsung Electronics Launches AI Lab in Montreal, Canada

SAIL Montreal @ ICML 2023

2023-07-23

SAIL Montreal is happy to have a strong presence at ICML 2023. Our office manager Geneviève Bernard will be present on site along with some of our research scientist who are happy to have a chat with you.

SAIL Montreal @ NeurIPS 2022

2022-11-28

SAIL Montreal is happy to sponsor NeurIPS 2022! We will have a booth where you can meet some of our research scientists.

What is SAIL Montreal?

SAIL published papers (80)

People

VP, Lab Director

Research Scientists

Office Manager

Samsung Visiting Researchers

Alumni Research Scientists

Related Content