Doina Precup

Sumana Basu

Collaborating Alumni - McGill University

Co-supervisor :

Adriana Romero Soriano

Collaborating Alumni - McGill University

Lynn Cherif

Collaborating Alumni - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Principal supervisor :

David Meger

Jonathan Colaço Carr

Master's Research - McGill University

Principal supervisor :

Prakash Panangaden

Élodie Coté-Gauthier

Collaborating researcher - McGill University

Co-supervisor :

Isabeau Prémont-Schwarz

Franco Del Balso

Collaborating researcher - Université de Montréal

Jesse Farebrother

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

PhD - McGill University

Principal supervisor :

Collaborating researcher - Birla Institute of Technology

Howard Huang

PhD - McGill University

Haque Ishfaq

Collaborating Alumni - McGill University

Mohammad Sami Nur Islam Islam

Master's Research - McGill University

Arushi Jain

Collaborating Alumni - McGill University

PhD - Polytechnique Montréal

Martin Klissarov

PhD - McGill University

Postdoctorate - McGill University

Jonathan Lebensold

Collaborating Alumni - McGill University

Collaborating Alumni - McGill University

Ray Luo

PhD - McGill University

Principal supervisor :

G McCracken

PhD - McGill University

Nazanin Mohammadi Sepahvand

Collaborating Alumni - McGill University

Shahrad Mohammadzadeh

Master's Research - McGill University

Principal supervisor :

Gabriela Moisescu-Pareja

Collaborating researcher - McGill University

Co-supervisor :

Irina Rish

Padideh Nouri

PhD - Université de Montréal

Co-supervisor :

PhD - McGill University

Co-supervisor :

Nate Rahn

PhD - McGill University

Principal supervisor :

Marc Gendron-Bellemare

Sahand Rezaei-Shoshtari

PhD - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Co-supervisor :

PhD - McGill University

Nishanth Anand Vemgal

PhD - McGill University

PhD - McGill University

Co-supervisor :

Samira Ebrahimi Kahou

Research Intern - McGill University

Zihan Wang

PhD - McGill University

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Steve Wen

Master's Research - McGill University

Co-supervisor :

Gregory Dudek

Zijing Wu

PhD - McGill University

Principal supervisor :

PhD - McGill University

Harry Zhao

Collaborating Alumni - McGill University

Co-supervisor :

Blog Posts

Generic thumbnail for Mila Blog articles.

February 22, 2024

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Read the article

Publications

Unifying Mechanistic Interpretations of Neural Networks Trained on Modular Addition

Gabriela Moisescu-Pareja

Gavin McCracken

Vincent Létourneau

Jonathan Love

2025-09-21

NeurIPS.cc/2025/Workshop/WiML (published)

Capturing Individual Human Preferences with Reward Features

Andre Barreto

Vincent Dumoulin

Yiran Mao

Nicolas Perez-Nieves

Mark Rowland

Bobak Shahriari

Yann Dauphin

Hugo Larochelle

Reinforcement learning from human feedback usually models preferences using a reward model that does not distinguish between people. We argu… (see more)e that this is unlikely to be a good design choice in contexts with high potential for disagreement, like in the training of large language models. We propose a method to specialise a reward model to a person or group of people. Our approach builds on the observation that individual preferences can be captured as a linear combination of a set of general reward features. We show how to learn such features and subsequently use them to quickly adapt the reward model to a specific individual, even if their preferences are not reflected in the training data. We present experiments with large language models comparing the proposed architecture with a non-adaptive reward model and also adaptive counterparts, including models that do in-context personalisation. Depending on how much disagreement there is in the training data, our model either significantly outperforms the baselines or matches their performance with a simpler architecture and more stable training.

2025-09-17

NeurIPS.cc/2025/Conference (poster)

Plasticity as the Mirror of Empowerment

David Abel

Michael Bowling

Andre Barreto

Will Dabney

Shi Dong

Steven Hansen

Anna Harutyunyan

Khimya Khetarpal

Clare Lyle

Razvan Pascanu

Georgios Piliouras

Jonathan Richens

Mark Rowland

Tom Schaul

Satinder Singh

Agents are minimally entities that are influenced by their past observations and act to influence future observations. This latter capacity … (see more)is captured by empowerment, which has served as a vital framing concept across artificial intelligence and cognitive science. This former capacity, however, is equally foundational: In what ways, and to what extent, can an agent be influenced by what it observes? In this paper, we ground this concept in a universal agent-centric measure that we refer to as plasticity, and reveal a fundamental connection to empowerment. Following a set of desiderata on a suitable definition, we define plasticity using a new information-theoretic quantity we call the generalized directed information. We show that this new quantity strictly generalizes the directed information introduced by Massey (1990) while preserving all of its desirable properties. Under this definition, we find that plasticity is well thought of as the mirror of empowerment: The two concepts are defined using the same measure, with only the direction of influence reversed. Our main result establishes a tension between the plasticity and empowerment of an agent, suggesting that agent design needs to be mindful of both characteristics. We explore the implications of these findings, and suggest that plasticity, empowerment, and their relationship are essential to understanding agency

2025-09-17

NeurIPS.cc/2025/Conference (spotlight)

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks

Gavin McCracken

Gabriela Moisescu-Pareja

Vincent Létourneau

Jonathan Love

We propose a testable universality hypothesis, asserting that seemingly disparate neural network solutions observed in the simple task of mo… (see more)dular addition are unified under a common abstract algorithm. While prior work interpreted variations in neuron-level representations as evidence for distinct algorithms, we demonstrate - through multi-level analyses spanning neurons, neuron clusters, and entire networks - that multilayer perceptrons and transformers universally implement the abstract algorithm we call the approximate Chinese Remainder Theorem. Crucially, we introduce approximate cosets and show that neurons activate exclusively on them. Furthermore, our theory works for deep neural networks (DNNs). It predicts that universally learned solutions in DNNs with trainable embeddings or more than one hidden layer require only O(log n) features, a result we empirically confirm. This work thus provides the first theory-backed interpretation of multilayer networks solving modular addition. It advances generalizable interpretability and opens a testable universality hypothesis for group multiplication beyond modular addition.

2025-09-17

NeurIPS.cc/2025/Conference (poster)

Relative Trajectory Balance is equivalent to Trust-PCL

2025-08-31

ArXiv (preprint)

arxiv.org

Exploring Sparse Adapters for Scalable Merging of Parameter Efficient Experts

Minseon Kim

Riyasat Ohib

Lucas Caccia

Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly a… (see more)dapted on the fly for specific downstream tasks, without requiring additional fine-tuning. Typically, LoRA (Low-Rank Adaptation) serves as the foundational building block of such parameter-efficient modular architectures, leveraging low-rank weight structures to reduce the number of trainable parameters. In this paper, we study the properties of sparse adapters, which train only a subset of weights in the base neural network, as potential building blocks of modular architectures. First, we propose a simple method for training highly effective sparse adapters, which is conceptually simpler than existing methods in the literature and surprisingly outperforms both LoRA and full fine-tuning in our setting. Next, we investigate the merging properties of these sparse adapters by merging adapters for up to 20 natural language processing tasks, thus scaling beyond what is usually studied in the literature. Our findings demonstrate that sparse adapters yield superior in-distribution performance post-merging compared to LoRA or full model merging. Achieving strong held-out performance remains a challenge for all methods considered.

2025-07-06

colmweb.org/COLM/2025/Conference (accepted)

Language Agents Mirror Human Causal Reasoning Biases. How Can We Help Them Think Like Scientists?

Anthony GX-Chen

Dongyan Lin

Mandana Samiei

Blake Aaron Richards

Rob Fergus

Kenneth Marino

Language model (LM) agents are increasingly used as autonomous decision-makers who need to actively gather information to guide their decisi… (see more)ons. A crucial cognitive skill for such agents is the efficient exploration and understanding of the causal structure of the world -- key to robust, scientifically grounded reasoning. Yet, it remains unclear whether LMs possess this capability or exhibit systematic biases leading to erroneous conclusions. In this work, we examine LMs' ability to explore and infer causal relationships, using the well-established"Blicket Test"paradigm from developmental psychology. We find that LMs reliably infer the common, intuitive disjunctive causal relationships but systematically struggle with the unusual, yet equally (or sometimes even more) evidenced conjunctive ones. This"disjunctive bias"persists across model families, sizes, and prompting strategies, and performance further declines as task complexity increases. Interestingly, an analogous bias appears in human adults, suggesting that LMs may have inherited deep-seated reasoning heuristics from their training data. To this end, we quantify similarities between LMs and humans, finding that LMs exhibit adult-like inference profiles (but not children-like). Finally, we propose a test-time sampling method which explicitly samples and eliminates hypotheses about causal relationships from the LM. This scalable approach significantly reduces the disjunctive bias and moves LMs closer to the goal of scientific, causally rigorous reasoning.

2025-07-06

colmweb.org/COLM/2025/Conference (accepted)

An Artificial Intelligence-Based Model to Predict Pregnancy After Intrauterine Insemination: A Retrospective Analysis of 9501 Cycles

Jaume Minano Masip

Camille Grysole

Penelope Borduas

Isaac-Jacques Kadoch

Simon Phillips

Daniel Dufort

Background/Objectives: Intrauterine insemination (IUI) is a common first-line approach in the treatment of numerous infertile couples, espec… (see more)ially in cases of unexplained infertility. Its relatively low success rate, however, could benefit from the development of AI-based support tools to predict its outcome, thus helping the clinical management of patients undergoing IUI cycles. Our objective was to develop a robust and accurate machine learning model that predicts pregnancy outcomes following IUI. Methods: A retrospective, observational, and single-center study was conducted. In total, 3535 couples (aged 18–43 years) that underwent IUI between January 2011 and December 2015 were recruited. Twenty-one clinical and laboratory parameters of 9501 IUI cycles were used to train different machine learning algorithms. Accuracy of pregnancy outcome was evaluated by an area under the curve (AUC) analysis. Results: The linear SVM outperformed AdaBoost, Kernel SVM, Random Forest, Extreme Forest, Bagging, and Voting classifiers. Pre-wash sperm concentration, the ovarian stimulation protocol, cycle length, and maternal age were strong predictors of a positive pregnancy test following IUI (AUC = 0.78). Paternal age was found to be the worst predictor. Conclusions: Our Linear SVM model predicts a positive pregnancy outcome following IUI. Although this model shows value for the clinical management of infertile patients and informed decision-making by the patients, further validation using independent datasets is required prior to clinical implementation.

2025-06-30

Journal of Personalized Medicine (published)

Capacity-Constrained Continual Learning

Zheng Wen

Benjamin Van Roy

Satinder Singh

2025-06-30

arXiv (published)

arxiv.org

Revisiting Laplacian Representations for Value Function Approximation in Deep RL

Priyesh Vijayan

Padideh Nouri

Rishav

A. Chandar

Yash Chandak

Mathieu Reymond

S Ebrahimi Kahou

Proto-value functions (PVFs) introduced Laplacian embeddings as an effective feature basis for value-function approximation; however, their … (see more)utility remained limited to small, fully known state spaces. Recent work has scaled Laplacian embeddings to high-dimensional inputs, using them for reward shaping and option discovery in goal-directed tasks, yet only as auxiliary signals, rather than directly using them as features for value functions. In this paper, we learn Laplacian eigenvectors online and employ them as features for Q-learning in 23 Atari games. We empirically demonstrate that these online–learned embeddings substantially improve model-free RL in large, high-dimensional domains. We demonstrate that enriching state representations with action embeddings yields additional gains under both behavior-policy and uniform-random policies. Additionally, we introduce the Fusion architecture, which augments the representation with useful inductive bias at the embedding level. To assess the usefulness of each embedding used in the Fusion architecture, we use Shapley values analysis.

2025-06-21

rl-conference.cc/RLC/2025/Workshop/IBRL (published)

Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning

Martin Klissarov

Akhil Bagaria

Ziyan Luo

George Konidaris

Marlos C. Machado

Developing agents capable of exploring, planning and learning in complex open-ended environments is a grand challenge in artificial intellig… (see more)ence (AI). Hierarchical reinforcement learning (HRL) offers a promising solution to this challenge by discovering and exploiting the temporal structure within a stream of experience. The strong appeal of the HRL framework has led to a rich and diverse body of literature attempting to discover a useful structure. However, it is still not clear how one might define what constitutes good structure in the first place, or the kind of problems in which identifying it may be helpful. This work aims to identify the benefits of HRL from the perspective of the fundamental challenges in decision-making, as well as highlight its impact on the performance trade-offs of AI agents. Through these benefits, we then cover the families of methods that discover temporal structure in HRL, ranging from learning directly from online experience to offline datasets, to leveraging large language models (LLMs). Finally, we highlight the challenges of temporal structure discovery and the domains that are particularly well-suited for such endeavours.

2025-06-15

ArXiv (preprint)

arxiv.org

Robust Reward Modeling via Causal Rubrics

Pragya Srivastava

Harman Singh

Rahul Madhavan

Gandharv Patil

Sravanti Addepalli

Arun Suggala

Rengarajan Aravamudhan

Soumya Sharma

Anirban Laha

Aravindan Raghuveer

Karthikeyan Shanmugam

Reward models (RMs) for LLM alignment often exhibit reward hacking, mistaking spurious correlates (e.g., length, format) for causal quality … (see more)drivers (e.g., factuality, relevance), leading to brittle RMs. We introduce CROME (Causally Robust Reward Modeling), a causally-grounded framework using targeted augmentations to mitigate this. CROME employs: (1) Causal Augmentations, pairs isolating specific causal attribute changes, to enforce sensitivity, and (2) Neutral Augmentations, tie-labeled pairs varying spurious attributes while preserving causal content, to enforce invariance. Crucially, augmentations target LLM-identified causal rubrics, requiring no prior knowledge of spurious factors. CROME significantly outperforms baselines on RewardBench (Avg +5.4\%, Safety +13.2\%, Reasoning +7.2\%) and demonstrates enhanced robustness via improved Best-of-N performance across RewardBench, WildGuardTest, and GSM8k.

2025-06-09

ICML.cc/2025/Workshop/MoFA (poster)