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

Continue Reading

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.

We are hiring!

We are hiring research scientists! Scroll down on that page for more information about the position and how to apply.

Accepted papers at NeurIPS 2022

Click the links for more information on these papers (requires NeurIPS registration).

• The Curse of Unrolling: Rate of Differentiating Through Optimization [arxiv]
  Damien Scieur, Quentin Bertrand, Gauthier Gidel and Fabian Pedregosa
  Wed 30 Nov 11:30 a.m. CST — 1 p.m. CST @ Hall J #724

• Model Zoos: A Dataset of Diverse Populations of Neural Network Models [arxiv]
  Konstantin Schürholt, Diyar Taskiran, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth
  Wed 30 Nov 11:30 a.m. CST — 1 p.m. CST @ Hall J #1017

• Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights [arxiv]
  Konstantin Schürholt, Boris Knyazev, Xavier Giró-i-Nieto, Damian Borth
  Thu 1 Dec 11:30 a.m. CST — 1 p.m. CST @ Hall J #605

• MCVD: Masked Conditional Video Diffusion for Prediction [arxiv]
  Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal
  Thu 1 Dec 11:30 a.m. CST — 1 p.m. CST @ Hall J #921
  Spotlight: Tue 6 Dec 8 p.m. CST — 8:15 p.m. CST

• Data-Efficient Structured Pruning via Submodular Optimization [arxiv]
  Marwa El Halabi, Suraj Srinivas, Simon Lacoste-Julien
  Thu 1 Dec 11:30 a.m. CST — 1 p.m. CST @ Hall J #938

Finding us

The following research scientists will be available in-person at NeurIPS 2022:

• Damien Scieur
• Reza Babanezhad
• Marwa El Halabi
• Yan Zhang
• Jihye Kim (Visiting Research Scientist)
• Aristide Baratin

You can find the full list of people on our main website.

Booth

Our booth will be at the Expo hall #224. Our office manager Geneviève Bernard will be there most of the time, with a rotating cast of research scientists.

Workshops

Our research scientist Alexia Jolicoeur-Martineau co-organizes the Workshop on Score-Based Methods on Friday December 2 in Room 293-294.

We also have some workshop papers:

• Unlocking Slot Attention by Changing Optimal Transport Costs
  Yan Zhang*, David W Zhang*, Simon Lacoste-Julien, Gertjan J. Burghouts, Cees G. M. Snoek
  Poster at All Things Attention, December 2 (hybrid in-person and virtual)

• Equivariance With Learned Canonicalization Functions
  Sékou-Oumar Kaba*, Arnab Kumar Mondal*, Yan Zhang, Yoshua Bengio, Siamak Ravanbakhsh
  Oral at Symmetry and Geometry in Neural Representations, December 3 (in-person)

• Target-based Surrogates for Stochastic Optimization
  J. Wilder Lavington, Sharan Vaswani, Reza Babanezhad, Mark Schmidt, Nicolas Le Roux
  Poster at Optimization for Machine Learning, December 3 (in-person)

• Unlocking Slot Attention by Changing Optimal Transport Costs
  Yan Zhang*, David W Zhang*, Simon Lacoste-Julien, Gertjan J. Burghouts, Cees G. M. Snoek
  Oral at Neuro Causal and Symbolic AI, December 9 (virtual)