Home

Inspiring the development of artificial intelligence for the benefit of all 

A professor talks to his students in a café/lounge.

Located in the heart of Quebec’s AI ecosystem, Mila is a community of more than 1,200 researchers specializing in machine learning and dedicated to scientific excellence and innovation.

About

Featured
Featured
Featured

News

01 May 2025
Follow Mila researchers at AISTATS 2025
Logo Mila and AISTATS
Read the story
29 Apr 2025
Mila Techaide 2025 Raises over $110,000 in Donations
Picture of David Adelani speaking in front of an audience at Mila
Read the story
24 Apr 2025
Innovasea Partners with Mila to Advance AI Innovation in the Blue Economy
logo Mila and Innovasea
Read the story
See more news

Faculty 

Founded in 1993 by Professor Yoshua Bengio, Mila today brings together over 140 professors affiliated with Université de Montréal, McGill University, Polytechnique Montréal and HEC Montréal. Mila also welcomes professors from Université Laval, Université de Sherbrooke, École de technologie supérieure (ÉTS) and Concordia University. 

Browse the online directory

Photo of Yoshua Bengio

Latest Publications

Evaluating machine learning-driven intrusion detection systems in IoT: Performance and energy consumption
Saeid Jamshidi
Kawser Wazed Nafi
Amin Nikanjam
Foutse Khomh
2025-06-01
Computers & Industrial Engineering (published)
doi.org
arxiv.org
STAMP: Differentiable Task and Motion Planning via Stein Variational Gradient Descent
Yewon Lee
Andrew Zou Li
Yizhou Huang
Philip Huang
Eric Heiden
Krishna Murthy
Fabian Damken
Kevin A. Smith
Derek Nowrouzezahrai
Fabio Ramos
Florian Shkurti
Carnegie-mellon University
M. I. O. Technology
Technische Universitat Darmstadt
Nvidia
M. University
University of Sydney
Planning for many manipulation tasks, such as using tools or assembling parts, often requires both symbolic and geometric reasoning. Task an… (see more)d Motion Planning (TAMP) algorithms typically solve these problems by conducting a tree search over high-level task sequences while checking for kinematic and dynamic feasibility. While performant, most existing algorithms are highly inefficient as their time complexity grows exponentially with the number of possible actions and objects. Additionally, they only find a single solution to problems in which many feasible plans may exist. To address these limitations, we propose a novel algorithm called Stein Task and Motion Planning (STAMP) that leverages parallelization and differentiable simulation to efficiently search for multiple diverse plans. STAMP relaxes discrete-and-continuous TAMP problems into continuous optimization problems that can be solved using variational inference. Our algorithm builds upon Stein Variational Gradient Descent, a gradient-based variational inference algorithm, and parallelized differentiable physics simulators on the GPU to efficiently obtain gradients for inference. Further, we employ imitation learning to introduce action abstractions that reduce the inference problem to lower dimensions. We demonstrate our method on two TAMP problems and empirically show that STAMP is able to: 1) produce multiple diverse plans in parallel; and 2) search for plans more efficiently compared to existing TAMP baselines.
2025-06-01
IEEE Robotics and Automation Letters (published)
doi.org
openreview.net
Mitigating Goal Misgeneralization via Minimax Regret
Karim Ahmed Abdel Sadek
Matthew Farrugia-Roberts
Hannah Erlebach
Christian Schroeder de Witt
David Scott Krueger
Usman Anwar
Michael D Dennis
Robustness research in reinforcement learning often focuses on ensuring that the policy consistently exhibits capable, goal-driven behavior.… (see more) However, not every capable behavior is the intended behavior. *Goal misgeneralization* can occur when the policy generalizes capably with respect to a 'proxy goal' whose optimal behavior correlates with the intended goal on the training distribution, but not out of distribution. Though the intended goal would be ambiguous if they were perfectly correlated in training, we show progress can be made if the goals are only *nearly ambiguous*, with the training distribution containing a small proportion of *disambiguating* levels. We observe that the training signal from disambiguating levels could be amplified by regret-based prioritization. We formally show that approximately optimal policies on maximal-regret levels avoid the harmful effects of goal misgeneralization, which may exist without this prioritization. Empirically, we find that current regret-based Unsupervised Environment Design (UED) methods can mitigate the effects of goal misgeneralization, though do not always entirely eliminate it. Our theoretical and empirical results show that as UED methods improve they could further mitigate goal misgeneralization in practice.
2025-05-09
rl-conference.cc/RLC/2025/Conference (accepted)
openreview.net
openreview.net
"It was 80% me, 20% AI": Seeking Authenticity in Co-Writing with Large Language Models
Angel Hsing-Chi Hwang
Q. Vera Liao
Su Lin Blodgett
Alexandra Olteanu
Adam Trischler
2025-05-02
Proceedings of the ACM on Human-Computer Interaction (published)
doi.org
arxiv.org
See more publications

AI for Humanity

Socially responsible and beneficial development of AI is a fundamental component of Mila’s mission. As a leader in the field, we wish to contribute to social dialogue and the development of applications that will benefit society.

Learn more

A person looks up at a starry sky.