Publications

Offline Model-Based Optimization: Comprehensive Review

Minsu Kim

Jiayao Gu

Zixuan Liu

Can Chen

2025-03-21

ArXiv (prépublication)

RL4Med-DDPO: Reinforcement Learning for Controlled Guidance Towards Diverse Medical Image Generation using Vision-Language Foundation Models

Mohammed Mohammed

Zahra TehraniNasab

2025-03-20

ArXiv (prépublication)

Meditation induces shifts in neural oscillations, brain complexity and critical dynamics: Novel insights from MEG

Annalisa Pascarella

Philipp Thölke

David Meunier

Jordan O’Byrne

Tarek Lajnef

Antonino Raffone

Roberto Guidotti

Vittorio Pizzella

Laura Marzetti

2025-03-19

bioRxiv (prépublication)

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction

Xiangru Jian

Kevin Qinghong Lin

Juan A. Rodriguez

Montek Kalsi

Nicolas Chapados

M. T. ¨Ozsu

Aishwarya Agrawal

David Vazquez

Perouz Taslakian

Sai Rajeswar

Human Annotator

2025-03-19

ArXiv (prépublication)

Hitting the right pitch: Cortical tracking of fundamental frequency changes across speech rates in auditory and sensorimotor regions

Yorguin-Jose Mantilla-Ramos

Ana-Sofía Hincapié-Casas

Annalisa Pascarella

Tarek Lajnef

Richard M. Leahy

Emily B.J. Coffey

Véronique Boulenger

2025-03-18

bioRxiv (prépublication)

Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs

Nicolas Le Roux

Marc Gendron-Bellemare

Jonathan Lebensold

Arnaud Bergeron

Joshua Greaves

Alex Fr'echette

Carolyne Pelletier

Eric Thibodeau-Laufer

S'andor Toth

Sam Work

2025-03-18

ArXiv (prépublication)

Tapered Off-Policy REINFORCE: Stable and efficient reinforcement learning for LLMs

Nicolas Le Roux

Marc Gendron-Bellemare

Jonathan Lebensold

Arnaud Bergeron

Joshua Greaves

Alex Fr'echette

Carolyne Pelletier

Eric Thibodeau-Laufer

S'andor Toth

Sam Work

2025-03-18

ArXiv (prépublication)

Sparse Decomposition of Graph Neural Networks

Yaochen Hu

Mai Zeng

Ge Zhang

Pavel Rumiantsev

Yingxue Zhang

2025-03-17

TMLR (accepté)

Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies

Rashid A. Mushkani

Shin (Alexandre) Koseki

2025-03-16

ArXiv (prépublication)

Sample Compression for Continual Learning

Mathieu Bazinet

2025-03-13

ArXiv (prépublication)

Sample Compression for Continual Learning

Mathieu Bazinet

2025-03-13

ArXiv (prépublication)

Sample Compression for Self Certified Continual Learning

Mathieu Bazinet

Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existi… (voir plus)ng continual learning approaches in the literature rely on heuristics and do not provide learning guarantees. In this paper, we present a new method called Continual Pick-to-Learn (CoP2L), which is able to retain the most representative samples for each task in an efficient way. CoP2L combines the Pick-to-Learn algorithm (rooted in the sample compression theory) and the experience replay continual learning scheme. This allows us to provide non-vacuous upper bounds on the generalization loss of the learned predictors, numerically computable after each task. We empirically evaluate our approach on several standard continual learning benchmarks across Class-Incremental, Task-Incremental, and Domain-Incremental settings. Our results show that CoP2L is highly competitive across all setups, often outperforming existing baselines, and significantly mitigating catastrophic forgetting compared to vanilla experience replay in the Class-Incremental setting. It is possible to leverage the bounds provided by CoP2L in practical scenarios to certify the predictor reliability on previously learned tasks, in order to improve the trustworthiness of the continual learning algorithm.

2025-03-13

ArXiv (prépublication)