Publications

The implicated scientist: on the role of AI researchers in the development of weapons systems
Alexandra Volokhova
Alex Hernández-García
Artificial intelligence (AI) technologies are increasingly used in modern weapons systems. Notably, these systems have recently been involve… (voir plus)d in mass killings and destruction at scale. Furthermore, there is currently a strong interest and competition among powerful players to accelerate the proliferation of weapons with automated or AI-based components, a phenomenon known as AI arms race. This competition poses a risk of causing even more deaths and devastation in the future, as well as increased power and wealth inequality. In this work, we aim to shed light on the role of AI researchers as implicated subjects in the harms caused by weapons enabled by AI technologies. We investigate and discuss the specifics of this implication and explore ways to transfigure this position of implication into one of differentiated, long-distance solidarity with the victims of technologically fortified injustices.
2026-04-19
arXiv (prépublication)
doi.org
arxiv.org
Beyond Distribution Sharpening: The Importance of Task Rewards
Sarthak Mittal
Leo Gagnon
Guillaume Lajoie
Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into t… (voir plus)heir training pipelines, enabling systems to evolve from pure reasoning models into sophisticated agents. However, debate persists regarding whether RL genuinely instills new skills within a base model or merely sharpens its existing distribution to elicit latent capabilities. To address this dichotomy, we present an explicit comparison between distribution sharpening and task-reward-based learning, utilizing RL as a tool to implement both paradigms. Our analysis reveals the inherent limitations of distribution sharpening, demonstrating from first principles how and why the optima can be unfavorable and the approach fundamentally unstable. Furthermore, our experiments using Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct and Qwen3-4B-Instruct-2507 on math datasets confirm that sharpening yields limited gains, whereas incorporating task-based reward signal can greatly help achieve robust performance improvements and stable learning.
2026-04-16
arXiv (prépublication)
doi.org
arxiv.org
NaijaS2ST: A Multi-Accent Benchmark for Speech-to-Speech Translation in Low-Resource Nigerian Languages
Marie Maltais
Yejin Jeon
Min Ma
Shamsuddeen Hassan Muhammad
Idris Abdulmumin
Maryam Ibrahim Mukhtar
Daud Abolade
Joel Okepefi
Johnson Sewedo
David Ifeoluwa Adelani
Speech translation for low-resource languages remains fundamentally limited by the scarcity of high-quality, diverse parallel speech data, a… (voir plus) challenge that is especially pronounced in African linguistic contexts. To address this, we introduce NaijaS2ST, a parallel speech translation dataset spanning Igbo, Hausa, Yor\`ub\'a, and Nigerian Pidgin paired with English. The dataset comprises approximately 50 hours of speech per language and captures substantial variation in speakers and accents, reflecting realistic multilingual and multi-accent conditions. With NaijaS2ST, we conduct a comprehensive benchmark of cascaded, end-to-end (E2E), and AudioLLM-based approaches across bidirectional translation settings. Our results show that audio LLMs with few-shot examples are more effective for speech-to-text translation than cascaded and end-to-end methods trained on fine-tuned data. However, for speech-to-speech translation, the cascaded and audio LLM paradigms yield comparable performance, indicating that there is still considerable room for improvement in developing targeted, task-specific models for this setting. By providing both a high-quality dataset and a systematic benchmark, we hope that NaijaS2ST will serve as a strong foundation for advancing research in low-resource, multilingual speech translation.
2026-04-16
arXiv (prépublication)
doi.org
arxiv.org
Reexploring drivers of technological variation through the complex landscapes of cultural evolution.
James Clark
L. Timbrell
S. E. Paris
Gonzalo J. Linares-Matás
2026-04-16
Journal of anthropological sciences = Rivista di antropologia : JASS (publié)
doi.org
A Universal Systematic Method to Generate Error Patterns on Memoryless Channels
Marwan Jalaleddine
Jiajie Li
Syed Mohsin Abbas
Warren J. Gross
The high computational cost of approaching the performance of Maximum-likelihood (ML) decoding has limited its practical use for decades. Be… (voir plus)cause the complexity grows exponentially with the message length, researchers have spent years developing algorithms like Ordered Statistics Decoding (OSD), Partial Ordered Statistics Decoding (POSD) and Guessing Random Additive Noise decoding (GRAND) which try to approach ML performance. OSD, POSD and GRAND work by trying to guess the error patterns affecting the received signals. However, there does not exist a systematic method to extend the error pattern guesses to novel channels. This work introduces a systematic method that uses the Probability Density Function (PDF) of a memoryless channel to generate a set of error patterns that can be applied on any future received signal on this channel. Simulation results show that our proposed method applied on GRAND, OSD and POSD generally matches or outperforms current pre-generated error patterns on additive white Gaussian noise (AWGN) channel, mixture of Gaussian distribution channels, Rayleigh fading channel with perfect knowledge of Channel State Information (CSI) and Rayleigh fading channel with no perfect knowledge of Channel State Information (NCSI).
2026-04-16
arXiv (prépublication)
doi.org
arxiv.org
Why Open Source? A Game-Theoretic Analysis of the AI Race
Andjela Mladenovic
Aaron Courville
Gauthier Gidel
In recent years, with the advancement of frontier AI, we have observed certain dynamics in open-sourcing and closed-sourcing decisions. We p… (voir plus)ropose a game-theoretic model to analyze these dynamics in the current landscape of the AI race. Our model builds on an R&D race framework under a winner-takes-all setting, and it accounts for the cases where the players' actions can be either discrete or continuous (i.e., partial open-sourcing, such as open weights). We show that determining the existence of a discrete pure non-trivial Nash equilibrium is NP-hard in general but that we can transform the discrete Nash existence computation into a MIP (Mixed-Integer Programming) problem, making it tractable for small instances using a standard MIP solver. Next, we show the existence and tractability of pure Nash equilibria in the continuous version of our problem, leveraging standard convex analysis results, and constructing an equivalent MIP formulation. Throughout this work, we leverage both our main technical results as well as surrounding technical analysis, to derive socially relevant insights that we believe can serve both to understand already existing decisions and dynamics and to potentially inform new policies.
2026-04-16
arXiv (prépublication)
doi.org
arxiv.org
The Golden Rule of Big Memory: Persistence Is Not Harmful
Yu Hua
Xue Liu
Ion Stoica
Seeking a transformative memory scheme that grows in performance and capacity as the infrastructure expands.
2026-04-15
Communications of the ACM (publié)
doi.org
Neurovascular Coupling as Early, High-Sensitive Biomarker for Cognitive Decline and Vascular Pathology: Protocol for Systematic Review and Meta-Analysis
V. D. Abramova
Veronika Egovtseva
Ksenya Pronyaeva
Shamsa H. Alshamsi
Marta Estrada
Rustam Talybov
Taleb~M. Almansoori
Bassem Sadek
Mohammed Khogali
Mohammad~I.K. Hamad
Milos Ljubisavljevic
Danilo Bzdok
Yauhen Statsenko
2026-04-14
Research Square (accepté)
doi.org
RobotPan: A 360$^\circ$ Surround-View Robotic Vision System for Embodied Perception
Jiahao Ma
Qiang Zhang
Peiran Liu
Zeran Su
Pihai Sun
Gang Han
Wen Zhao
Wei Cui
Zhang Zhang
Zhiyuan Xu
Renjing Xu
Jian Tang
Miaomiao Liu
Yijie Guo
Surround-view perception is increasingly important for robotic navigation and loco-manipulation, especially in human-in-the-loop settings su… (voir plus)ch as teleoperation, data collection, and emergency takeover. However, current robotic visual interfaces are often limited to narrow forward-facing views, or, when multiple on-board cameras are available, require cumbersome manual switching that interrupts the operator's workflow. Both configurations suffer from motion-induced jitter that causes simulator sickness in head-mounted displays. We introduce a surround-view robotic vision system that combines six cameras with LiDAR to provide full 360
2026-04-14
arXiv (prépublication)
doi.org
arxiv.org
AI Methods for Implementation Science (AIM-IS): developing a framework, toolkit, and reporting standard for the responsible use of AI in implementation practice and research
Guillaume Fontaine
Susan Michie
Rinad S. Beidas
Elvin Geng
Christine Fahim
Byron J. Powell
Vivian Welch
James Thomas
J. Chan
Samira Abbasgholizadeh-Rahimi
France Légaré
Janna Hastings
Sylvie D. Lambert
Justin Presseau
Sharon E. Straus
Ruopeng An
Ashrita Saran
Natalie Taylor
Open Science Framework, March 15, 2026: https://doi.org/10.17605/OSF.IO/BX35K.
2026-04-13
Implementation Science (publié)
doi.org
Translating Brain Encoding Models to Clinical Cohorts: Challenges of Domain Adaptation
Lune Bellec
Marie St‐Laurent
Julie Boyle
Basile Pinsard
Elizabeth DuPré
We’ve optimized fMRI biomarkers to generalize across participants, not cognitive states. Brain encoding models might finally let us model … (voir plus)both and change what “good data” means. These are the slides of a presentation by Dr Lune Bellec at the AI4health workshop, ÉTS, Montréal, Feb 2026.
2026-04-13
Zenodo (inconnu)
doi.org
Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions
Manuela González‐González
Soufiane Belharbi
Muhammad Zeeshan
Masoumeh Sharafi
Muhammad Haseeb Aslam
Lorenzo Sia
Nicolas Richet
Marco Pedersoli
Alessandro L. Koerich
Simon L Bacon
Eric Granger
Using behavioural science, health interventions focus on behaviour change by providing a framework to help patients acquire and maintain hea… (voir plus)lthy habits that improve medical outcomes. In-person interventions are costly and difficult to scale, especially in resource-limited regions. Digital health interventions offer a cost-effective approach, potentially supporting independent living and self-management. Automating such interventions, especially through machine learning, has gained considerable attention recently. Ambivalence and hesitancy (A/H) play a primary role for individuals to delay, avoid, or abandon health interventions. A/H are subtle and conflicting emotions that place a person in a state between positive and negative evaluations of a behaviour, or between acceptance and refusal to engage in it. They manifest as affective inconsistency across modalities or within a modality, such as language, facial, vocal expressions, and body language. While experts can be trained to recognize A/H, integrating them into digital health interventions is costly and less effective. Automatic A/H recognition is therefore critical for the personalization and cost-effectiveness of digital health interventions. Here, we explore the application of deep learning models for A/H recognition in videos, a multi-modal task by nature. In particular, this paper covers three learning setups: supervised learning, unsupervised domain adaptation for personalization, and zero-shot inference via large language models (LLMs). Our experiments are conducted on the unique and recently published BAH video dataset for A/H recognition. Our results show limited performance, suggesting that more adapted multi-modal models are required for accurate A/H recognition. Better methods for modeling spatio-temporal and multimodal fusion are necessary to leverage conflicts within/across modalities.
2026-04-12
arXiv (prépublication)
doi.org
arxiv.org