Publications

LLMs and Stack Overflow discussions: Reliability, impact, and challenges

Leuson Da Silva

Jordan Samhi

Foutse Khomh

2025-07-01

Journal of Systems and Software (publié)

doi.org

LLMs and Stack Overflow discussions: Reliability, impact, and challenges

Leuson Da Silva

Jordan Samhi

Foutse Khomh

2025-07-01

Journal of Systems and Software (publié)

doi.org

arxiv.org

Mixed-integer Second-Order Cone Programming for Multi-period Scheduling of Flexible AC Transmission System Devices

Mohamad Charara

Martin De Montigny

Nivine Abou Daher

Hanane Dagdougui

Antoine Lesage-Landry

2025-07-01

arXiv (publié)

doi.org

arxiv.org

Model approximation in MDPs with unbounded per-step cost

Berk Bozkurt

Aditya Mahajan

Ashutosh Nayyar

Yi Ouyang

We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process …

2025-07-01

IEEE Transactions on Automatic Control (publié)

doi.org

arxiv.org

A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment

Jean-Philippe Corbeil

Amin Dada

Jean-Michel Attendu

Asma Ben Abacha

Alessandro Sordoni

Lucas Caccia

Franccois Beaulieu

Thomas Lin

Jens Kleesiek

Paul Vozila

High computation costs and latency of large language models such as GPT-4 have limited their deployment in clinical settings. Small language… (voir plus) models (SLMs) offer a cost-effective alternative, but their limited capacity requires biomedical domain adaptation, which remains challenging. An additional bottleneck is the unavailability and high sensitivity of clinical data. To address these challenges, we propose a novel framework for adapting SLMs into high-performing clinical models. We introduce the MediPhi collection of 3.8B-parameter SLMs developed with our novel framework: pre-instruction tuning of experts on relevant medical and clinical corpora (PMC, Medical Guideline, MedWiki, etc.), model merging, and clinical-tasks alignment. To cover most clinical tasks, we extended the CLUE benchmark to CLUE+, doubling its size. Our expert models deliver relative improvements on this benchmark over the base model without any task-specific fine-tuning: 64.3% on medical entities, 49.5% on radiology reports, and 44% on ICD-10 coding (outperforming GPT-4-0125 by 14%). We unify the expert models into MediPhi via model merging, preserving gains across benchmarks. Furthermore, we built the MediFlow collection, a synthetic dataset of 2.5 million high-quality instructions on 14 medical NLP tasks, 98 fine-grained document types, and JSON format support. Alignment of MediPhi using supervised fine-tuning and direct preference optimization achieves further gains of 18.9% on average.

2025-07-01

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (publié)

doi.org

arxiv.org

Modulation of leg trajectory by transcranial magnetic stimulation during walking

H. Bourgeois

Rose Guay-Hottin

El-Mehdi Meftah

Marina Martinez

Marco Bonizzato

D. Barthélemy

2025-07-01

Scientific Reports (publié)

doi.org

Multi-Armed Sampling Problem and the End of Exploration

Mohammad Pedramfar

Siamak Ravanbakhsh

This paper introduces the framework of multi-armed sampling, as the sampling counterpart to the optimization problem of multi-arm bandits. O… (voir plus)ur primary motivation is to rigorously examine the exploration-exploitation trade-off in the context of sampling. We systematically define plausible notions of regret for this framework and establish corresponding lower bounds. We then propose a simple algorithm that achieves these optimal regret bounds. Our theoretical results demonstrate that in contrast to optimization, sampling does not require exploration. To further connect our findings with those of multi-armed bandits, we define a continuous family of problems and associated regret measures that smoothly interpolates and unifies multi-armed sampling and multi-armed bandit problems using a temperature parameter. We believe the multi-armed sampling framework, and our findings in this setting can have a foundational role in the study of sampling including recent neural samplers, akin to the role of multi-armed bandits in reinforcement learning. In particular, our work sheds light on the need for exploration and the convergence properties of algorithm for entropy-regularized reinforcement learning, fine-tuning of pretrained models and reinforcement learning with human feedback (RLHF).

2025-07-01

arXiv (publié)

doi.org

arxiv.org

Multiscale Neural PDE Surrogates for Prediction and Downscaling: Application to Ocean Currents

Abdessamad El-Kabid

Loubna Benabbou

Redouane Lguensat

Alex Hernandez-Garcia

Accurate modeling of physical systems governed by partial differential equations is a central challenge in scientific computing. In oceanogr… (voir plus)aphy, high-resolution current data are critical for coastal management, environmental monitoring, and maritime safety. However, available satellite products, such as Copernicus data for sea water velocity at ~0.08 degrees spatial resolution and global ocean models, often lack the spatial granularity required for detailed local analyses. In this work, we (a) introduce a supervised deep learning framework based on neural operators for solving PDEs and providing arbitrary resolution solutions, and (b) propose downscaling models with an application to Copernicus ocean current data. Additionally, our method can model surrogate PDEs and predict solutions at arbitrary resolution, regardless of the input resolution. We evaluated our model on real-world Copernicus ocean current data and synthetic Navier-Stokes simulation datasets.

2025-07-01

arXiv (publié)

doi.org

arxiv.org

Optimizers Qualitatively Alter Solutions And We Should Leverage This

Razvan Pascanu

Clare Lyle

Ionut-Vlad Modoranu

Naima Elosegui Borras

Dan Alistarh

Petar Veličković

Sarath Chandar

Soham De

James Martens

Due to the nonlinear nature of Deep Neural Networks (DNNs), one can not guarantee convergence to a unique global minimum of the loss when us… (voir plus)ing optimizers relying only on local information, such as SGD. Indeed, this was a primary source of skepticism regarding the feasibility of DNNs in the early days of the field. The past decades of progress in deep learning have revealed this skepticism to be misplaced, and a large body of empirical evidence shows that sufficiently large DNNs following standard training protocols exhibit well-behaved optimization dynamics that converge to performant solutions. This success has biased the community to use convex optimization as a mental model for learning, leading to a focus on training efficiency, either in terms of required iteration, FLOPs or wall-clock time, when improving optimizers. We argue that, while this perspective has proven extremely fruitful, another perspective specific to DNNs has received considerably less attention: the optimizer not only influences the rate of convergence, but also the qualitative properties of the learned solutions. Restated, the optimizer can and will encode inductive biases and change the effective expressivity of a given class of models. Furthermore, we believe the optimizer can be an effective way of encoding desiderata in the learning process. We contend that the community should aim at understanding the biases of already existing methods, as well as aim to build new optimizers with the explicit intent of inducing certain properties of the solution, rather than solely judging them based on their convergence rates. We hope our arguments will inspire research to improve our understanding of how the learning process can impact the type of solution we converge to, and lead to a greater recognition of optimizers design as a critical lever that complements the roles of architecture and data in shaping model outcomes.

2025-07-01

arXiv (publié)

doi.org

arxiv.org

Perpetua: Multi-Hypothesis Persistence Modeling for Semi-Static Environments

Miguel Saavedra-Ruiz

Samer B. Nashed

Charlie Gauthier

Liam Paull

Many robotic systems require extended deployments in complex, dynamic environments. In such deployments, parts of the environment may change… (voir plus) between subsequent robot observations. Most robotic mapping or environment modeling algorithms are incapable of representing dynamic features in a way that enables predicting their future state. Instead, they opt to filter certain state observations, either by removing them or some form of weighted averaging. This paper introduces Perpetua, a method for modeling the dynamics of semi-static features. Perpetua is able to: incorporate prior knowledge about the dynamics of the feature if it exists, track multiple hypotheses, and adapt over time to enable predicting of future feature states. Specifically, we chain together mixtures of"persistence"and"emergence"filters to model the probability that features will disappear or reappear in a formal Bayesian framework. The approach is an efficient, scalable, general, and robust method for estimating the states of features in an environment, both in the present as well as at arbitrary future times. Through experiments on simulated and real-world data, we find that Perpetua yields better accuracy than similar approaches while also being online adaptable and robust to missing observations.

2025-07-01

arXiv (publié)

doi.org

arxiv.org

Pixel Perfect MegaMed: A Megapixel-Scale Vision-Language Foundation Model for Generating High Resolution Medical Images

2025-07-01

arXiv (publié)

doi.org