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 1,400 researchers specializing in machine learning and dedicated to scientific excellence and innovation.

About

Featured

News

22 Oct 2026
AI in the Service of Wildfire Management in Canada
Birds view eye of a forest
Read the story
08 Oct 2026
Mila and Inria Strengthen Canada-France AI Research Cooperation
Bruno Sportisse, Chairman and CEO of Inria and Valérie Pisano, President and CEO of Mila.
Read the story
06 Oct 2026
Five Mila Members Appointed Canada-CIFAR AI Chairs
picture of 5 mila members appointed canada cifar ai chairs
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

Adaptive Order Policies for Masked Diffusion
Jama Hussein Mohamud
Mohsin Hasan
Mirco Ravanelli
Yoshua Bengio
Masked diffusion models have seen great success in capturing data distributions over discrete sequences in domains such as text and proteins… (see more). These models generate data by iteratively unmasking tokens starting from a fully masked sequence, with the unmasking order typically chosen at random or using a heuristic based on denoiser probabilities. In this work, we propose a scheme for learning the unmasking order using an additional lightweight policy network on top of a diffusion model. Our proposed loss reweights terms in the masked diffusion loss according to policy probabilities, and results in a policy that prefers positions where the denoiser is more likely to be correct. We study this loss in two settings: (i) training solely the policy while using a frozen pre-trained denoiser, and (ii) training the policy and denoiser jointly with the weighted loss to allow for mutual adaptation. We demonstrate that our approach outperforms common heuristics on problems that are sensitive to token ordering, such as combinatorial problems, proteins as well as various coding and language tasks.
2026-12-30
OpenReview (published)
doi.org
openreview.net
DASB - Discrete Audio and Speech Benchmark
Pooneh Mousavi
Jarod Duret
Darius Petermann
Artem Ploujnikov
Luca Della Libera
Anastasia Kuznetsova
Cem Subakan
Mirco Ravanelli
Duret, Jarod
Kuznetsova, Anastasia
Discrete audio tokens have recently gained considerable attention for their potential to bridge audio and language processing, enabling mult… (see more)imodal language models that can both generate and understand audio. However, preserving key information such as phonetic content, speaker identity, and paralinguistic cues remains a major challenge. Identifying the optimal tokenizer and configuration is further complicated by inconsistent evaluation settings across existing studies. To address this, we introduce the Discrete Audio and Speech Benchmark (DASB), a comprehensive framework for benchmarking discrete audio tokens across speech, general audio, and music domains on a range of discriminative and generative tasks. Our results show that discrete representations are less robust than continuous ones and require careful tuning of factors such as model architecture, data size, learning rate, and capacity. Semantic tokens generally outperform acoustic tokens, but a gap remains between discrete tokens and continuous features, highlighting the need for further research. DASB codes, evaluation setup, and leaderboards are publicly available at https://poonehmousavi.github.io/DASB-website/.
2026-12-30
OpenReview (published)
doi.org
openreview.net
Do Tabular Foundation Models Know Physics? Contamination, Units, and the Deterministic Limit
Wassim Tenachi
Yashar Hezaveh
Laurence Perreault Levasseur
Pierre-Luc Bacon
Tabular foundation models (TFMs) learn to fill in tables the way language models fill in text, and tables are arguably the format in which m… (see more)ost physical measurement arrives. Did they learn any physics in the process? They are Bayesian by construction, so the question is what their prior contains. We probe it directly, evaluating four of them (TabPFN-3, TabICLv2, TabDPT and Real-TabPFN-2.5) against six baselines on datasets sampled from 316 physical equations, in and out of domain. TFMs dominate, out of the box and after tuning. But we show that their prior can represent neither a noiseless mechanism nor physical units, which is why they interpolate physics without yet being able to act as physical models.
2026-12-30
OpenReview (published)
doi.org
openreview.net
ECUAS: A family of metrics for principled evaluation of uncertainty-augmented systems
Lautaro Estienne
Erik Ernst
Matias Vera
Pablo Piantanida
LUCIANA FERRER
In high-stakes automated decision-making, access to predictive uncertainty is essential for enabling users -- human or downstream systems --… (see more) to accept or reject predictions based on application-specific cost trade-offs. Such uncertainty-augmented (UA) systems -- i.e., systems that output both predictions and uncertainty scores -- are currently being assessed in the literature in a variety of ways, using separate metrics to evaluate the predictions and the uncertainty scores, setting a cost function with a fixed rejection cost or integrating over a coverage-risk curve. We argue that these evaluation approaches are inadequate for assessing overall performance of the UA system for decision making under uncertainty and propose a novel family of metrics, ECUAS
2026-12-30
OpenReview (published)
openreview.net
openreview.net
See more publications
Mila Ventures

Mila Ventures

Our venture arm cultivates the next generation of companies backed by Mila's world-class AI research ecosystem. We invest in visionary founders building at the frontier of deep tech, AI, STEM, and beyond.

We believe the future will be shaped by Venture Scientists.

Learn more

A person looks up at a starry sky.