Publications

Multiple-model coding scheme for electrical signal compression
Corentin Presvôts
Michel Kieffer
Thibault Prevost
Patrick Panciatici
Zuxing Li
Pablo Piantanida
2025-03-31
Signal Processing (publié)
doi.org
Negative Language Transfer Identification in the English Writing of Chinese and Farsi Native Speakers
Mohammad Karimiabdolmaleki
Leticia Farias Wanderley
Maria Cutumisu
Mohsen Rezazadeh
Carrie Demmans Epp
2025-03-31
International Journal of Artificial Intelligence in Education (publié)
doi.org
Neural Kinematic Bases for Fluids
Yibo Liu
Paul Kry
Kenny Erleben
Noam Aigerman
Sune Darkner
Teseo Schneider
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Neurophysiological effects of targeting sleep spindles with closed-loop auditory stimulation
Hugo R Jourde
Milo Sobral
Giovanni Beltrame
Emily B J Coffey
Sleep spindles are neural events unique to nonrapid eye movement sleep that play key roles in memory reactivation and consolidation. However… (voir plus), much of the evidence for their function remains correlational rather than causal. Closed-loop brain stimulation uses real-time monitoring of neural events (often via electroencephalography; EEG) to deliver precise auditory, magnetic, or electrical stimulation for research or therapeutic purposes. Automated online algorithms to detect and stimulate sleep spindles have recently been validated, but the time- and frequency-resolved physiological responses generated by them have not yet been documented. Building on the recent findings that sleep spindles do not block the transmission of sound to cortex, the present work investigates the neurophysiological responses to closed-loop auditory stimulation of sleep spindles. EEG data were collected from 10 healthy human adults (6 nights each), whilst sleep spindles were detected and in half the nights, targeted with auditory stimulation. Spindles were successfully stimulated before their offset in 97.6% of detections and did not disturb sleep. Comparing stimulation with sham, we observed that stimulation resulted in increased sigma activity (11–16 Hz) at about 1 second poststimulation but that stimulation occurring at the beginning of the spindle also resulted in early termination of the spindle. Finally, we observed that stimulating an evoked spindle did not elicit additional sigma activity. Our results validate the use of closed-loop auditory stimulation targeting sleep spindles, and document its neural effects, as a basis for future causal investigations concerning spindles’ roles in memory consolidation.
2025-03-31
Sleep Advances (publié)
doi.org
Online Interior-point Methods for Time-varying Equality-constrained Optimization
Jean-Luc Lupien
Iman Shames
Antoine Lesage-Landry
2025-03-31
IEEE Transactions on Automatic Control (publié)
doi.org
arxiv.org
Performance Smells in ML and Non-ML Python Projects: A Comparative Study
Franccois Belias
Leuson Da Silva
Foutse Khomh
Cyrine Zid
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Prism: Dynamic and Flexible Benchmarking of LLMs Code Generation with Monte Carlo Tree Search
Vahid Majdinasab
Amin Nikanjam
Foutse Khomh
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition
Muhammad Osama Zeeshan
Marco Pedersoli
Alessandro Lameiras Koerich
Eric Grange
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Scaling Language-Free Visual Representation Learning
David Fan
Shengbang Tong
Jiachen Zhu
Koustuv Sinha
Zhuang Liu
Xinlei Chen
Michael G. Rabbat
Nicolas Ballas
Yann Lecun
Amir Bar
Saining Xie
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Sliced-Wasserstein Distance-based Data Selection
Julien Pallage
Antoine Lesage-Landry
We propose a new unsupervised anomaly detection method based on the sliced-Wasserstein distance for training data selection in machine learn… (voir plus)ing approaches. Our filtering technique is interesting for decision-making pipelines deploying machine learning models in critical sectors, e.g., power systems, as it offers a conservative data selection and an optimal transport interpretation. To ensure the scalability of our method, we provide two efficient approximations. The first approximation processes reduced-cardinality representations of the datasets concurrently. The second makes use of a computationally light Euclidian distance approximation. Additionally, we open the first dataset showcasing localized critical peak rebate demand response in a northern climate. We present the filtering patterns of our method on synthetic datasets and numerically benchmark our method for training data selection. Finally, we employ our method as part of a first forecasting benchmark for our open-source dataset.
2025-03-31
arXiv (publié)
doi.org
arxiv.org
TAPNext: Tracking Any Point (TAP) as Next Token Prediction
Artem Zholus
Carl Doersch
Yi Yang
Skanda Koppula
Viorica Patraucean
Xu Owen He
Ignacio Rocco
Mehdi S. M. Sajjadi
A. Chandar
Ross Goroshin
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Towards Assessing Deep Learning Test Input Generators
Seif Mzoughi
Ahmed Haj Yahmed
Mohamed Elshafei
Foutse Khomh
Diego Elias Costa
2025-03-31
arXiv (publié)
doi.org
arxiv.org