Publications

Offline Model-Based Optimization: Comprehensive Review
Minsu Kim
Jiayao Gu
Ye Yuan
Taeyoung YUN
Zixuan Liu
Yoshua Bengio
Can Chen
2025-03-21
ArXiv (preprint)
arxiv.org
arxiv.org
RL4Med-DDPO: Reinforcement Learning for Controlled Guidance Towards Diverse Medical Image Generation using Vision-Language Foundation Models
Parham Saremi
Amar Kumar
Mohammed Mohammed
Zahra TehraniNasab
Tal Arbel
2025-03-20
ArXiv (preprint)
arxiv.org
arxiv.org
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
Karim Jerbi
2025-03-19
bioRxiv (preprint)
doi.org
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
Shravan Nayak
Xiangru Jian
Kevin Qinghong Lin
Juan A. Rodriguez
Montek Kalsi
Rabiul Awal
Nicolas Chapados
M. T. ¨Ozsu
Aishwarya Agrawal
David Vazquez
Chris Pal
Perouz Taslakian
Spandana Gella
Sai Rajeswar
Human Annotator
2025-03-19
ArXiv (preprint)
arxiv.org
arxiv.org
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
Karim Jerbi
Véronique Boulenger
2025-03-18
bioRxiv (preprint)
doi.org
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 (preprint)
doi.org
arxiv.org
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 (preprint)
arxiv.org
arxiv.org
Sparse Decomposition of Graph Neural Networks
Yaochen Hu
Mai Zeng
Ge Zhang
Pavel Rumiantsev
Liheng Ma
Yingxue Zhang
Mark Coates
2025-03-17
TMLR (accepted)
doi.org
openreview.net
Negotiative Alignment: Embracing Disagreement to Achieve Fairer Outcomes -- Insights from Urban Studies
Rashid A. Mushkani
Hugo Berard
Shin (Alexandre) Koseki
2025-03-16
ArXiv (preprint)
arxiv.org
arxiv.org
Sample Compression for Continual Learning
Jacob Comeau
Mathieu Bazinet
Pascal Germain
Cem Subakan
2025-03-13
ArXiv (preprint)
arxiv.org
arxiv.org
Sample Compression for Continual Learning
Jacob Comeau
Mathieu Bazinet
Pascal Germain
Cem Subakan
2025-03-13
ArXiv (preprint)
doi.org
arxiv.org
Sample Compression for Self Certified Continual Learning
Jacob Comeau
Mathieu Bazinet
Pascal Germain
Cem Subakan
Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existi… (see more)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 (preprint)
arxiv.org
arxiv.org