Publications

Leveraging Per-Instance Privacy for Machine Unlearning
Nazanin Mohammadi Sepahvand
Anvith Thudi
Berivan Isik
Ashmita Bhattacharyya
Nicolas Papernot
Eleni Triantafillou
Daniel M. Roy
Gintare Karolina Dziugaite
2025-07-14
International Conference on Machine Learning (Accept (poster))
doi.org
proceedings.mlr.press
Neural activity resolved in space and time through fusion of large-scale EEG and fMRI datasets.
Ian Charest
Peter Brotherwood
Mathias Salvas-Hébert
Kendrick Kay
Frédéric Gosselin
2025-07-14
Journal of Vision (published)
doi.org
Relative Entropy Pathwise Policy Optimization
Claas Voelcker
Axel Brunnbauer
Marcel Hussing
Michal Nauman
Pieter Abbeel
Eric R. Eaton
Radu Grosu
Amir-massoud Farahmand
Igor Gilitschenski
Score-function policy gradients have delivered strong results in game-playing, robotics and language-model fine-tuning. Yet its high-varianc… (see more)e often undermines training stability. On the other hand, pathwise policy gradients alleviate the training variance, but are reliable only when driven by an accurate action-conditioned value function which is notoriously hard to train without relying on past off-policy data. In this paper, we discuss how to construct a value-gradient driven, on-policy algorithm that allow training Q-value models purely from on-policy data, unlocking the possibility of using pathwise policy updates in the context of on-policy learning. We show how to balance stochastic policies for exploration with constrained policy updates for stable training, and evaluate important architectural components that facilitate accurate value function learning. Building on these insights, we propose Relative Entropy Pathwise Policy Optimization (REPPO), an efficient on-policy algorithm that combines the sample-efficiency of pathwise policy gradients with the simplicity and minimal memory footprint of standard on-policy learning. We demonstrate that REPPO provides strong empirical performance at decreased sample requirements, wall-clock time, memory footprint as well as high hyperparameter robustness in a set of experiments on two standard GPU-parallelized benchmarks.
2025-07-14
ArXiv (preprint)
doi.org
arxiv.org
STAGED: A Multi-Agent Neural Network for Learning Cellular Interaction Dynamics
João Felipe Rocha
Ke Xu
Xingzhi Sun
Ananya Krishna
Dhananjay Bhaskar
Blanche Mongeon
Morgan Craig
Mark B. Gerstein
Smita Krishnaswamy
The advent of single-cell technology has significantly improved our understanding of cellular states and subpopulations in various tissues u… (see more)nder normal and diseased conditions by employing data-driven approaches such as clustering and trajectory inference. However, these methods consider cells as independent data points of population distributions. With spatial transcriptomics, we can represent cellular organization, along with dynamic cell-cell interactions that lead to changes in cell state. Still, key computational advances are necessary to enable the data-driven learning of such complex interactive cellular dynamics. While agent-based modeling (ABM) provides a powerful framework, traditional approaches rely on handcrafted rules derived from domain knowledge rather than data-driven approaches. To address this, we introduce Spatio Temporal Agent-Based Graph Evolution Dynamics(STAGED) integrating ABM with deep learning to model intercellular communication, and its effect on the intracellular gene regulatory network. Using graph ODE networks (GDEs) with shared weights per cell type, our approach represents genes as vertices and interactions as directed edges, dynamically learning their strengths through a designed attention mechanism. Trained to match continuous trajectories of simulated as well as inferred trajectories from spatial transcriptomics data, the model captures both intercellular and intracellular interactions, enabling a more adaptive and accurate representation of cellular dynamics.
2025-07-14
ArXiv (preprint)
doi.org
arxiv.org
Effects of a Virtual Reality Hypnosis Intervention on Chronic Pain: A User Experience and Proof-of-concept Study
Alexandra Chevestrier-Lefeuvre
Joséphine Guiné
Jade Véronneau
Julie Lebeau
Floriane Rousseaux
Audrey Laurin
Marie-Fania Simard
Nadia Godin
Karim Jerbi
Philippe Richebé
Mathieu Landry
Pierre Rainville
Valentyn Fournier
David Ogez
Abstract

Chronic pain is a significant public health issue in Canada, with approximately one in four Canadians ove… (see more)r the age of 15 living with this condition. Due to its impact on individuals—both physically and psychologically—and its financial burden on the healthcare system, it is crucial to develop cost-effective and efficient treatment methods. Hypnosis and virtual reality have emerged as promising solutions in this context. This study aims to evaluate the preliminary efficacy and feasibility of an intervention combining virtual reality and hypnosis. The study involved 30 patients with chronic pain who were invited to test a hypnosis application delivered through a virtual reality device. Levels of pain, anxiety, and relaxation were measured before and after the intervention, while satisfaction, cybersickness, and user experience were evaluated post-intervention. At the end of the intervention, participants were invited to participate in a semi-structured interview to provide feedback on their satisfaction with the experience. Participants reported high levels of satisfaction with the intervention, a positive user experience, and minimal symptoms of cybersickness. The intervention was effective in reducing anxiety (W = 173.5, p = .002) and pain (W = 253.5, p< .001) while significantly enhancing relaxation levels (W = 9.00, p< .001). This intervention demonstrated effectiveness in reducing pain and anxiety while improving relaxation levels among individuals with chronic pain, paving the way for further investigations of the involved mechanisms.

2025-07-13
Research Square (preprint)
doi.org
Frequency enrichment of coding variants in a French-Canadian founder population and its implication for inflammatory bowel diseases
Claude Bhérer
Jean-Christophe Grenier
Justin Pelletier
Gabrielle Boucher
Genevieve Gagnon
Philippe Goyette
Dariel Ashton-Beaucage
Christine Stevens
Robert Battat
Alain Bitton
Philippe M Campeau
Catherine Laprise
Quebec IBD Genetics Consortium
Hailiang Huang
Mark Daly
Daniel Taliun
Julie G Hussin
Vincent Mooser
John D Rioux
The genetic features of founder populations with recent bottlenecks, causing some deleterious variants to rise to higher frequencies, can en… (see more)hance the power of rare variant association studies. French Canadians from Quebec represent a recent founder population with a particular disease heritage comprising more than 30 prevalent Mendelian conditions. Here, we characterize coding variation in this founder population using exome sequencing data from 2,820 French-Canadian participants - patients with inflammatory bowel diseases (IBD), parents and controls from the Quebec IBD cohort. We find that 18% of rare coding variants are 10-100 times more frequent than in non-Finnish Europeans (NFE). A total of 4,133 missense and loss-of-function variants were significantly enriched with a median 28-fold enrichment, revealing the potential for genotype-phenotype associations in this population. We describe significantly enriched pathogenic variants, including those known to account for the increased prevalence of rare diseases in FC compared to other European descent populations, such as Agenesis of corpus callosum and peripheral neuropathy (SLC12A6) and Leigh Syndrome French Canadian type (LRPPRC). Finally, we investigate whether rare protein-coding variants, enriched in French Canadians by the founder effect, contribute to the risk of IBD using trio and case/control cohorts. In addition to replicating associations in NOD2 and IL23R, we identified new candidate association signals, including enriched variants in SLC35E3, and ARSA. Our findings show that, even in well-characterized founder populations like the French Canadians, there remains untapped potential for genetic discovery, revealing both rare and complex disease risk factors through enriched coding variation.
2025-07-13
medRxiv (preprint)
doi.org
Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrieval
Arthur Satouf
Gabriel Ben-Zenou
Benjamin Piwowarski
Habiboulaye Amadou-Boubacar
Pablo Piantanida
Current sparse neural information retrieval (IR) methods, and to a lesser extent more traditional models such as BM25, do not take into acco… (see more)unt the document collection and the complex interplay between different term weights when representing a single document. In this paper, we show how the Rational Speech Acts (RSA), a linguistics framework used to minimize the number of features to be communicated when identifying an object in a set, can be adapted to the IR case -- and in particular to the high number of potential features (here, tokens). RSA dynamically modulates token-document interactions by considering the influence of other documents in the dataset, better contrasting document representations. Experiments show that incorporating RSA consistently improves multiple sparse retrieval models and achieves state-of-the-art performance on out-of-domain datasets from the BEIR benchmark. https://github.com/arthur-75/Rational-Retrieval-Acts
2025-07-12
International ACM SIGIR Conference on Research and Development in Information Retrieval (published)
doi.org
arxiv.org
Prompt4Trust: A Reinforcement Learning Prompt Augmentation Framework for Clinically-Aligned Confidence Calibration in Multimodal Large Language Models
Anita Kriz
Elizabeth Laura Janes
Xing Shen
Tal Arbel
Multimodal large language models (MLLMs) hold considerable promise for applications in healthcare. However, their deployment in safety-criti… (see more)cal settings is hindered by two key limitations: (i) sensitivity to prompt design, and (ii) a tendency to generate incorrect responses with high confidence. As clinicians may rely on a model's stated confidence to gauge the reliability of its predictions, it is especially important that when a model expresses high confidence, it is also highly accurate. We introduce Prompt4Trust, the first reinforcement learning (RL) framework for prompt augmentation targeting confidence calibration in MLLMs. A lightweight LLM is trained to produce context-aware auxiliary prompts that guide a downstream task MLLM to generate responses in which the expressed confidence more accurately reflects predictive accuracy. Unlike conventional calibration techniques, Prompt4Trust specifically prioritizes aspects of calibration most critical for safe and trustworthy clinical decision-making. Beyond improvements driven by this clinically motivated calibration objective, our proposed method also improves task accuracy, achieving state-of-the-art medical visual question answering (VQA) performance on the PMC-VQA benchmark, which is composed of multiple-choice questions spanning diverse medical imaging modalities. Moreover, our framework trained with a small downstream task MLLM showed promising zero-shot generalization to larger MLLMs in our experiments, suggesting the potential for scalable calibration without the associated computational costs. This work demonstrates the potential of automated yet human-aligned prompt engineering for improving the the trustworthiness of MLLMs in safety critical settings. Our codebase can be found at https://github.com/xingbpshen/prompt4trust.
2025-07-11
ArXiv (preprint)
doi.org
arxiv.org
RL, but don't do anything I wouldn't do
Michael K. Cohen
Marcus Hutter
Yoshua Bengio
Stuart Russell
In reinforcement learning (RL), if the agent's reward differs from the designers' true utility, even only rarely, the state distribution res… (see more)ulting from the agent's policy can be very bad, in theory and in practice. When RL policies would devolve into undesired behavior, a common countermeasure is KL regularization to a trusted policy ("Don't do anything I wouldn't do"). All current cutting-edge language models are RL agents that are KL-regularized to a "base policy" that is purely predictive. Unfortunately, we demonstrate that when this base policy is a Bayesian predictive model of a trusted policy, the KL constraint is no longer reliable for controlling the behavior of an advanced RL agent. We demonstrate this theoretically using algorithmic information theory, and while systems today are too weak to exhibit this theorized failure precisely, we RL-finetune a language model and find evidence that our formal results are plausibly relevant in practice. We also propose a theoretical alternative that avoids this problem by replacing the "Don't do anything I wouldn't do" principle with "Don't do anything I mightn't do".
2025-07-10
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence (published)
proceedings.mlr.press
proceedings.mlr.press
Multivariate Time-Series Anomaly Detection with Contaminated Data: Application to Physiological Signals
Thi Kieu Khanh Ho
Narges Armanfard
2025-07-10
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence (published)
doi.org
proceedings.mlr.press
scE2TM improves single-cell embedding interpretability and reveals cellular perturbation signatures
Hegang Chen
Yuyin Lu
Yifan Zhao
Zhiming Dai
Fu Lee Wang
Qing Li 0001
Yanghui Rao
Yuemei Li
2025-07-10
ArXiv (preprint)
doi.org
arxiv.org
Discrete Feynman-Kac Correctors
Mohsin Hasan
Viktor Ohanesian
Artem Gazizov
Yoshua Bengio
Alán Aspuru-Guzik
Roberto Bondesan
Marta Skreta
Kirill Neklyudov
Discrete diffusion models have recently emerged as a promising alternative to the autoregressive approach for generating discrete sequences.… (see more) Sample generation via gradual denoising or demasking processes allows them to capture hierarchical non-sequential interdependencies in the data. These custom processes, however, do not assume a flexible control over the distribution of generated samples. We propose Discrete Feynman-Kac Correctors, a framework that allows for controlling the generated distribution of discrete masked diffusion models at inference time. We derive Sequential Monte Carlo (SMC) algorithms that, given a trained discrete diffusion model, control the temperature of the sampled distribution (i.e. perform annealing), sample from the product of marginals of several diffusion processes (e.g. differently conditioned processes), and sample from the product of the marginal with an external reward function, producing likely samples from the target distribution that also have high reward. Notably, our framework does not require any training of additional models or fine-tuning of the original model. We illustrate the utility of our framework in several applications including: efficient sampling from the annealed Boltzmann distribution of the Ising model, improving the performance of language models for code generation and amortized learning, as well as reward-tilted protein sequence generation.
2025-07-08
ICML.cc/2025/Workshop/AI4MATH (poster)
doi.org
openreview.net