Publications

The Moral Consistency Pipeline: Continuous Ethical Evaluation for Large Language Models
Saeid Jamshidi
Kawser Wazed Nafi
Arghavan Moradi Dakhel
Negar Shahabi
Foutse Khomh
2025-12-01
ArXiv (preprint)
doi.org
arxiv.org
Training neural networks from scratch in a videogame leads to brittle brain encoding
François Paugam
Basile Pinsard
Marie St-Laurent
Guillaume Lajoie
Lune Bellec
Recent brain-encoding studies using videogame tasks suggest that the training objective of an artificial neural network plays a central role… (see more) in how well the network’s representations align with brain activity. This study investigates the alignment of artificial neural network activations with brain activity elicited by a video game task using models trained from scratch in controlled settings. We specifically compared three model training objectives: reinforcement learning, imitation learning, and a vision task, while accounting for other potential factors which may impact performance such as training data and model architecture. We tested models on brain encoding, i.e. their ability to predict functional magnetic resonance imaging (fMRI) signals acquired while human subjects played different levels of the video game Super Mario Bros. When tested on new playthroughs from the game levels seen at training, the reinforcement learning objective had a small but significant advantage in brain encoding, followed by the imitation learning and vision models. We hypothesized that brain-aligned representations would emerge only in task-competent models, and that the specific brain regions well encoded by a model would depend on the nature of the task it was trained on. While brain encoding did improve during model training, even an untrained model with matching architecture approached the performance of the best models. Contrary to our hypotheses, no model layers or specific training objectives aligned preferentially with specific brain areas. Large performance gaps also persisted in fully trained models across game levels, both those seen during training and entirely novel ones. Overall, even though reinforcement learning presented a small advantage to train brain encoding models for videogame data, all tested brain encoding models exhibited brittle performance with limited generalization both within- and out-of-distribution. Overall, our results suggest that training small artificial models from scratch is not sufficiently reliable, and that incorporating pretrained models such as foundation vision–action models may ultimately be necessary to support robust inferences about brain representations.
2025-12-01
bioRxiv (preprint)
doi.org
Accelerated Inorganic Materials Design with Generative Al Agents
Izumi Takahara
Teruyasu Mizoguchi
Bang Liu
Designing inorganic crystalline materials with tailored properties is critical to technological innovation, yet current generative computati… (see more)onal methods often struggle to efficiently explore desired targets with sufficient interpretability. Here, we present MatAgent, a generative approach for inorganic materials discovery that harnesses the powerful reasoning capabilities of large language models (LLMs). By combining a diffusion-based generative model for crystal structure estimation with a predictive model for property evaluation, MatAgent uses iterative, feedback-driven guidance to steer material exploration precisely toward user-defined targets. Integrated with external cognitive tools-including short-term memory, long-term memory, the periodic table, and a comprehensive materials knowledge base-MatAgent emulates human expert reasoning to vastly expand the accessible compositional space. Our results demonstrate that MatAgent robustly directs exploration toward desired properties while consistently achieving high compositional validity, uniqueness, and material novelty. This framework thus provides a highly interpretable, practical, and versatile AI-driven solution to accelerate the discovery and design of next-generation inorganic materials.
2025-11-30
Cell Reports Physical Science (published)
doi.org
arxiv.org
Biomechanical finite element simulation of the pelvic organs under dynamic loading and validation against experimental data from magnetic resonance imaging.
Camille Lafond
Louise Hohnadel
Thomas Brunel
Nicolas Pirró
Bellemare Marc-Emmanuel
Dominique Chamoret
Sébastien Roth
2025-11-30
Medical Engineering & Physics (published)
doi.org
Building a library of acute traumatic spinal cord injury images across Canada: a retrospective cohort study protocol
Naama Rotem-Kohavi
Suzanne Humphreys
Vanessa K Noonan
Christiana L Cheng
Mathieu Guay-Paquet
Maxime Bouthillier
Jan Valosek
Enamundram Naga Karthik
Emma Lichtenstein
Nick Guenther
Kalum Ost
Naj Attabib
Michael Hardisty
Jetan Badhiwala
Jeremie Larouche
Markian Pahuta
Sean Christie
Michael G Fehlings
Daryl Fourney
Brian K Kwon … (see 6 more)
Jean Marc Mac-Thiong
Jérôme Paquet
Philippe Phan
Christopher Witiw
Julien Cohen-Adad
David W Cadotte
MRI is increasingly recognised as a valuable tool for assessing prognosis and predicting outcomes following traumatic spinal cord injury (SC… (see more)I). Several potential MRI biomarkers have been identified, but efforts are still needed to improve the accuracy and feasibility of these biomarkers in clinical practice. This study aims to build a national Canadian SCI imaging repository for storing and analysing imaging data for SCI, with the goal of improving SCI MRI biomarkers to predict outcomes and inform clinical management. As a substudy of the Rick Hansen SCI Registry (RHSCIR), this retrospective multisite study includes individuals who sustained a traumatic cervical SCI between 2015 and 2021, were previously enrolled in RHSCIR, and had MRI scans acquired within 72 hours of injury and before any surgical intervention. Individuals with a penetrating trauma and/or with any prior spine surgery are excluded. The study principal investigator and research associates, experienced with data curation and with the standardised format and specifications of the Brain Imaging Data Structure standard, guide the site’s curator on the steps to perform image deidentification and curation to create standardised datasets across all sites. These datasets are transferred to a Digital Research Alliance of Canada (‘the Alliance’) server designated for this project and concatenated to form the national Canadian SCI imaging repository (Neurogitea). We are using a semiautomated processing pipeline to quantify lesion morphology, together with additional imaging measures that are manually extracted from the images (for instance, the relative maximal spinal cord compression and the maximum canal compromise). Through linkage to RHSCIR clinical and epidemiological data already available on eligible participants, regression analysis is planned to predict neurological outcomes at discharge, including the American Spinal Injury Association Impairment Scale grade, upper and lower extremity motor and sensory scores. This protocol has been submitted by the participating sites to obtain ethics and institutional approvals prior to the study initiation at each site. All 12 sites across Canada have now obtained ethics and institutional approvals. Study results will be disseminated at local, national and international conferences and by journal publications.
2025-11-30
BMJ Open (published)
doi.org
On Global Applicability and Location Transferability of Generative Deep Learning Models for Precipitation Downscaling
Paula Harder
Christian Lessig
Matthew Chantry
Francis Pelletier
David Rolnick
2025-11-30
ArXiv (preprint)
doi.org
arxiv.org
What makes a good public EV charging station? A revealed preference study
Steven Lamontagne
Margarida Carvalho
Emma Frejinger
Ribal Atallah
To determine the optimal locations for electric vehicle charging stations, optimisation models need to predict which charging stations users… (see more) will select. We estimate discrete choice models to predict the usage of charging stations using only readily available information for charging network operators. Our parameter values are estimated from a unique, revealed preferences dataset of charging sessions in Montreal, Quebec. We find that user distance to stations, proximity to home areas, and the number of outlets at each station are significant factors for predicting station usage. Additionally, amenities near charging stations have a neutral effect overall, with some users demonstrating strong preference or aversion for these locations. High variability among the preferences of users highlight the importance of models which incorporate panel effects. Moreover, integrating mixed logit models within the optimization of charging station network design yields high-quality solutions, even when evaluated under other model specifications.
2025-11-30
Transportation Research Part D: Transport and Environment (published)
doi.org
arxiv.org
Shielded Controller Units for RL with Operational Constraints Applied to Remote Microgrids
Hadi Nekoei
Alexandre Blondin Mass'e
Rachid Hassani
A. Chandar
Vincent Mai
Reinforcement learning (RL) is a powerful framework for optimizing decision-making in complex systems under uncertainty, an essential challe… (see more)nge in real-world settings, particularly in the context of the energy transition. A representative example is remote microgrids that supply power to communities disconnected from the main grid. Enabling the energy transition in such systems requires coordinated control of renewable sources like wind turbines, alongside fuel generators and batteries, to meet demand while minimizing fuel consumption and battery degradation under exogenous and intermittent load and wind conditions. These systems must often conform to extensive regulations and complex operational constraints. To ensure that RL agents respect these constraints, it is crucial to provide interpretable guarantees. In this paper, we introduce Shielded Controller Units (SCUs), a systematic and interpretable approach that leverages prior knowledge of system dynamics to ensure constraint satisfaction. Our shield synthesis methodology, designed for real-world deployment, decomposes the environment into a hierarchical structure where each SCU explicitly manages a subset of constraints. We demonstrate the effectiveness of SCUs on a remote microgrid optimization task with strict operational requirements. The RL agent, equipped with SCUs, achieves a 24% reduction in fuel consumption without increasing battery degradation, outperforming other baselines while satisfying all constraints. We hope SCUs contribute to the safe application of RL to the many decision-making challenges linked to the energy transition.
2025-11-29
ArXiv (preprint)
doi.org
arxiv.org
Freeze, Diffuse, Decode: Geometry-Aware Adaptation of Pretrained Transformer Embeddings for Antimicrobial Peptide Design
Pankhil Gawade
Adam Izdebski
Myriam Lizotte
Kevin R. Moon
Jake S. Rhodes
Guy Wolf
Ewa Szczurek
2025-11-27
ArXiv (preprint)
doi.org
arxiv.org
Mirror effect of genomic deletions and duplications on cognitive ability across the human cerebral cortex
Kuldeep Kumar
Sayeh Kazem
Guillaume Huguet
Worrawat Engchuan
Jakub Kopal
Thomas Renne
Martineau Jean-Louis
Omar Shanta
Zohra Saci
Bhooma Thiruvahindrapuram
Jeffrey MacDonald
Josephine Mollon
Laura M Schultz
Emma E M Knowles
David Porteous
Gail Davies
Paul Redmond
Sarah Harris
Simon Cox
Gunter Schumann … (see 9 more)
Zdenka Pausova
Celia Greenwood
Tomáš Paus
Stephen Scherer
Laura Almasy
Jonathan Sebat
David Glahn
Guillaume Dumas
Sébastien Jacquemont
Cognitive deficits are common across many neurodevelopmental and psychiatric conditions, including those studied in the current set of PGC-C… (see more)NV papers. How changes in regional gene expression across the cerebral cortex influence cognitive ability remains unknown. Population variation in gene dosage—which significantly impacts gene expression—represents a unique paradigm to address this question. We developed a cerebral-cortex gene-set burden analysis (CC-GSBA) to associate a trait with genomic deletions and duplications that disrupt genes with similar expression profiles across 180 cortical regions. We performed CC-GSBA across 180 cortical regions to test associations with cognitive ability in 260,000 individuals from general population cohorts. Most cortical gene sets were associated with a decrease in cognitive ability when deleted or duplicated, and this novel approach revealed opposing cortical patterns for the effect sizes of deletions and duplications. These cortical patterns of effect sizes followed the cortical gradient previously characterized at the molecular, cellular, and functional levels. We show that genes with preferential expression in sensorimotor regions demonstrated the largest effect on cognition when deleted. At the opposing end of the cortical gradient, genes with preferential expression in multimodal association regions affected cognition the most when duplicated. These two gene dosage cortical patterns could not be explained by particular cell types, developmental epochs, or genetic constraints, highlighting the fact that the macroscopic network organization of the cerebral cortex is key to understanding the effects of gene dosage on cognitive traits.
2025-11-27
Research Square (preprint)
doi.org
Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning
Alexander Meulemans
Rajai Nasser
Maciej Wolczyk
Marissa A. Weis
Seijin Kobayashi
Blake Aaron Richards
Guillaume Lajoie
Angelika Steger
Marcus Hutter
James Manyika
Rif A. Saurous
João Sacramento
Blaise Agüera y Arcas
2025-11-26
ArXiv (preprint)
doi.org
arxiv.org
Enhancing decision-making in glioblastoma surgery through an explainable human-Al collaboration: an international multicenter model development and external validation study
Julius M. Kernbach
Urte Schroeder
Karlijn Hakvoort
Jonas Ort
Hussam Hamou
Danilo Bzdok
Yasin Temel
Pieter Kubben
Charlotte Weyland
Martin Wiesmann
Victor Staartjes
Kevin Akeret
Moira Vieli
Carlo Serra
Luca Regli
Stefan Grau
Lasse Dührsen
Franz Ricklefs
Oliver Schnell
David Ryan Ormond … (see 9 more)
Alexander Grote
Matthias Simon
Hagen Meredig
Marianne Schell
Martin Bendszus
Georg Neuloh
Hans Clusmann
Dieter-Henrik Heiland
Daniel Delev
Surgical resection improves survival in glioblastoma, yet predicting the extent of resection (EOR) remains highly challenging. We developed … (see more)and externally validated an explainable AI model to generate personalized EOR estimates in 811 glioblastoma patients undergoing microsurgical resection. EOR was categorized into gross-total (GTR), near-total (NTR), and subtotal resections (STR). An interpretable framework provided model explanations and sensitivity analyses to assess the model’s strengths and limitations. To demonstrate clinical impact, we compared the performance of the human expert (gold standard) with our AI model and a combined human-AI approach. External validation confirmed generalizability (AUC 0.78, CI 0.73-0.82). Class-specific AUCs were 0.75 (0.67-0.82) for GTR, 0.59 (0.50-0.69) for NTR, and 0.69 (0.53-0.85) for STR. Key predictors included KPS and NANO scores, age, tumor volume, and unfavorable anatomical locations. A combined human-AI collaboration outperformed human experts, with higher overall accuracies (0.53 to 0.94), F1 scores (0.30 to 0.92), and Cohen’s κ (0.41 to 0.84). Enhancing predictive performance through the clinician-AI collaboration, our explainable model supports preoperative planning and highlights the value of integrating machine intelligence into surgical decision-making.
2025-11-26
NPJ Precision Oncology (published)
doi.org