Publications

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems
Armstrong Foundjem
Lionel Nganyewou Tidjon
Leuson Da Silva
Probabilistic Modelling is Sufficient for Causal Inference
Bruno Mlodozeniec
David S. Krueger
Richard E. Turner
Causal inference is a key research area in machine learning, yet confusion reigns over the tools needed to tackle it. There are prevalent cl… (see more)aims in the machine learning literature that you need a bespoke causal framework or notation to answer causal questions. In this paper, we want to make it clear that you \emph{can} answer any causal inference question within the realm of probabilistic modelling and inference, without causal-specific tools or notation. Through concrete examples, we demonstrate how causal questions can be tackled by writing down the probability of everything. Lastly, we reinterpret causal tools as emerging from standard probabilistic modelling and inference, elucidating their necessity and utility.
Enhanced Multi-Class Arrhythmia Detection Using Generative Adversarial Networks for Minority Class Augmentation
Heba Ismail
Mohamed Adel Serhani
Benjamin C. M. Fung
Now is the time: operationalizing generative neurophenomenology through interpersonal methods
Anne Monnier
Lena Adel

Lived experience is shaped by intersubjective, social, cultural, and historical dimensions. For the past 30 years, neurophenomenology has… (see more) adopted an embodied perspective of the mind by integrating first-person experiential and third-person neurobehavioral perspectives. Indeed, the neurophenomenology pragmatic approach has embraced an embodied perspective of the mind by integrating experiential first-person and neurobehavioural third-person perspectives. Neurophenomenology reveals mutual constraints between both, as they co-constitute a person’s lived experience. This article emphasizes the intersubjective and social facets of lived experience as well as the readiness of the scientific community to use a "generative neurophenomenology" approach, envisioned in the 1990s by Francisco Varela. For this endeavour, we clarify three meanings of “generative” as it applies distinctly to generative phenomenology, generative passages, and generative models. Then, we propose to combine existing methods to update neurophenomenology program: First, by transitioning from individual to multiple people phenomenology methods that include intersubjectivity experience; second, by expanding traditional neuroscience to include measures of multimodal interpersonal synchrony; and third, by leveraging multiple computational tools to integrate different viewpoints, thereby enriching our understanding of lived experience; We also underscore the potential of diverse mathematical formalisms to capture aspects of human experience, all while underscoring that using computational approaches to model neurophenomenology does not entail endorsing computationalism as a grounding hypothesis of human experience. Finally, we illustrate the clinical relevance of this paradigm through two case studies in psychiatry—(1) with interactive dyads in autism and (2) with multiple members in family therapy sessions—demonstrating its translational potential.

SPECTRE: Spectral Pre-training Embeddings with Cylindrical Temporal Rotary Position Encoding for Fine-Grained sEMG-Based Movement Decoding
Zihan Weng
Chanlin Yi
Jing Lu
Fali Li
Dezhong Yao 0001
Jingming Hou
Yangsong Zhang
Peng Xu
Decoding fine-grained movement from non-invasive surface Electromyography (sEMG) is a challenge for prosthetic control due to signal non-sta… (see more)tionarity and low signal-to-noise ratios. Generic self-supervised learning (SSL) frameworks often yield suboptimal results on sEMG as they attempt to reconstruct noisy raw signals and lack the inductive bias to model the cylindrical topology of electrode arrays. To overcome these limitations, we introduce SPECTRE, a domain-specific SSL framework. SPECTRE features two primary contributions: a physiologically-grounded pre-training task and a novel positional encoding. The pre-training involves masked prediction of discrete pseudo-labels from clustered Short-Time Fourier Transform (STFT) representations, compelling the model to learn robust, physiologically relevant frequency patterns. Additionally, our Cylindrical Rotary Position Embedding (CyRoPE) factorizes embeddings along linear temporal and annular spatial dimensions, explicitly modeling the forearm sensor topology to capture muscle synergies. Evaluations on multiple datasets, including challenging data from individuals with amputation, demonstrate that SPECTRE establishes a new state-of-the-art for movement decoding, significantly outperforming both supervised baselines and generic SSL approaches. Ablation studies validate the critical roles of both spectral pre-training and CyRoPE. SPECTRE provides a robust foundation for practical myoelectric interfaces capable of handling real-world sEMG complexities.
Causally informed, multifactorial pathways linking cognition and personality to adolescent mental health
Jiadong Yan
Bin Wan
Paule Joanne Toussaint
Judy Chen
Gleb Bezgin
Yasser Iturria-Medina
Alan Evans
Sherif Karama
Adolescence is a sensitive period for the emergence of psychopathology. During this time, physiological changes and environmental exposures … (see more)jointly shape brain development and influence cognitive and personality maturation, collectively heightening vulnerability to mental disorders. However, the complexity of interactions between these factors has hindered a systems-level understanding of mental health and the causal roles of cognition and personality in psychopathology. In this study, we proposed a multifactorial causal framework integrating brain, pubertal, environmental, and behavioral factors to characterize heterogeneity in adolescent mental health trajectories at the individual level. We then investigated latent causal pathways linking cognition and personality to mental health outcomes and identified potential personalized intervention targets. Leveraging the Adolescent Brain Cognitive Development (ABCD) dataset ( N = 4,501), we analyzed 165 behavioral pairs connecting cognition and personality traits to mental health symptoms. Using cross-sectional multivariate mediation and longitudinal interaction-inclusive analyses, we identified 68 behavioral pairs showing significant causal relationships, with brain and environmental exposures contributing to most pathways, while pubertal factors exhibited limited involvement. Individualized interpretive analyses further revealed 23 pairs suggesting potential interventions with response rates exceeding 50%. Among these, behavioral inhibition, negative urgency, and processing speed emerged as the most common intervention targets, whereas psychosis symptoms and attention problems were the most likely issues to improve. Overall, our study advances a comprehensive framework capturing the multifactorial and heterogeneous nature of adolescent mental health, delineates specific causal pathways from cognitive and personality traits to psychopathology, and provides a principled basis for potential individualized intervention strategies.
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
The reasoning performance of large language models (LLMs) can be substantially improved by training them with reinforcement learning (RL). T… (see more)he RL objective for LLM training involves a regularization term, which is the reverse Kullback-Leibler (KL) divergence between the trained policy and the reference policy. Since computing the KL divergence exactly is intractable, various estimators are used in practice to estimate it from on-policy samples. Despite its wide adoption, including in several open-source libraries, there is no systematic study analyzing the numerous ways of incorporating KL estimators in the objective and their effect on the downstream performance of RL-trained models. Recent works show that prevailing practices for incorporating KL regularization do not provide correct gradients for stated objectives, creating a discrepancy between the objective and its implementation. In this paper, we further analyze these practices and study the gradients of several estimators configurations, revealing how design choices shape gradient bias. We substantiate these findings with empirical observations by RL fine-tuning \texttt{Qwen2.5-7B}, \texttt{Llama-3.1-8B-Instruct} and \texttt{Qwen3-4B-Instruct-2507} with different configurations and evaluating their performance on both in- and out-of-distribution tasks. Through our analysis, we observe that, in on-policy settings: (1) estimator configurations with biased gradients can result in training instabilities; and (2) using estimator configurations resulting in unbiased gradients leads to better performance on in-domain as well as out-of-domain tasks. We also investigate the performance resulting from different KL configurations in off-policy settings and observe that KL regularization can help stabilize off-policy RL training resulting from asynchronous setups.
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
Enamundram Naga Karthik
Emma Lichtenstein
Nick Guenther
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
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.
Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks
Emergent temporal abstractions in autoregressive models enable hierarchical reinforcement learning
Seijin Kobayashi
Yanick Schimpf
Maximilian Schlegel
Angelika Steger
Maciej Wolczyk
Johannes Von Oswald
Kaitlin Maile
Blake Aaron Richards
Rif A. Saurous
James Manyika
Blaise Agüera y Arcas
Alexander Meulemans
João Sacramento
Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecede… (see more)nted success on many problem domains. During RL, these models explore by generating new outputs, one token at a time. However, sampling actions token-by-token can result in highly inefficient learning, particularly when rewards are sparse. Here, we show that it is possible to overcome this problem by acting and exploring within the internal representations of an autoregressive model. Specifically, to discover temporally-abstract actions, we introduce a higher-order, non-causal sequence model whose outputs control the residual stream activations of a base autoregressive model. On grid world and MuJoCo-based tasks with hierarchical structure, we find that the higher-order model learns to compress long activation sequence chunks onto internal controllers. Critically, each controller executes a sequence of behaviorally meaningful actions that unfold over long timescales and are accompanied with a learned termination condition, such that composing multiple controllers over time leads to efficient exploration on novel tasks. We show that direct internal controller reinforcement, a process we term "internal RL", enables learning from sparse rewards in cases where standard RL finetuning fails. Our results demonstrate the benefits of latent action generation and reinforcement in autoregressive models, suggesting internal RL as a promising avenue for realizing hierarchical RL within foundation models.
Energy-Efficient Multi-LLM Reasoning for Binary-Free Zero-Day Detection in IoT Firmware
Saeid Jamshidi
Omar Abdul-Wahab
Martine Bellaiche
Securing Internet of Things (IoT) firmware remains difficult due to proprietary binaries, stripped symbols, heterogeneous architectures, and… (see more) limited access to executable code. Existing analysis methods, such as static analysis, symbolic execution, and fuzzing, depend on binary visibility and functional emulation, making them unreliable when firmware is encrypted or inaccessible. To address this limitation, we propose a binary-free, architecture-agnostic solution that estimates the likelihood of conceptual zero-day vulnerabilities using only high-level descriptors. The approach integrates a tri-LLM reasoning architecture combining a LLaMA-based configuration interpreter, a DeepSeek-based structural abstraction analyzer, and a GPT-4o semantic fusion model. The solution also incorporates LLM computational signatures, including latency patterns, uncertainty markers, and reasoning depth indicators, as well as an energy-aware symbolic load model, to enhance interpretability and operational feasibility. In addition, we formally derive the mathematical foundations of the reasoning pipeline, establishing monotonicity, divergence, and energy-risk coupling properties that theoretically justify the model's behavior. Simulation-based evaluation reveals that high exposure conditions increase the predicted zero-day likelihood by 20 to 35 percent across models, with GPT-4o demonstrating the strongest cross-layer correlations and the highest sensitivity. Energy and divergence metrics significantly predict elevated risk (p < 0.01), reinforcing the effectiveness of the proposed reasoning framework.
Hidden sampling biases inflate performance in gene regulatory network inference
Florin Ratajczak
Eva Hoermanseder
Jason Hartford
Pascal Falter-Braun
Matthias Heinig
Antonio Scialdone
Accurate reconstruction of gene regulatory networks (GRNs) from single-cell transcriptomic data remains a major methodological challenge. Re… (see more)cent machine learning approaches, particularly graph neural networks and graph autoencoders, have reported improved performance, yet these gains do not consistently translate to realistic biological settings. Here, we show that a key reason for that is the way negative regulatory interactions are sampled for supervised training and evaluation. We find that widely used sampling strategies introduce node-degree biases that allow models to exploit trivial graph-structural cues rather than biological signals. Across multiple benchmarks, simple degree-based heuristics match or exceed state-of-the-art graph neural network models under these biased evaluation protocols. We further introduce a degree-aware sampling approach that eliminates these artifacts and provides more reliable assessments of GRN inference methods. Our results call for standardized, bias-aware benchmarking practices to ensure meaningful progress in supervised GRN inference from single-cell RNA-seq data.