Publications

Advancements in Affective and Behavior Analysis: The 8th ABAW Workshop and Competition

Dimitrios D. Kollias

Panagiotis Tzirakis

Alan Cowen

Stefanos P. Zafeiriou

Irene Kotsia

Eric Granger

Marco Pedersoli

Simon Bacon

Alice Baird

Chris Gagne 0001

Chunchang Shao

Guanyu Hu

Soufiane Belharbi

Muhammad Haseeb Aslam

2025-01-01

CVPR Workshops (published)

dblp.uni-trier.de

Advocacy for Children With Surgical Diseases in Nigeria: National Policy Status, Gaps, and Solutions

Justina O. Seyi-Olajide

Ayla Gerk

Elena Guadagno

Adesoji Ademuyiwa

Emmanuel A. Ameh

Dan Poenaru

2025-01-01

Journal of Pediatric Surgery (published)

doi.org

Anti-patterns and Code Smells for Multi-language Systems

Mouna Abidi

Manel Grichi

Foutse Khomh

Yann‐Gaël Guéhéneuc

2025-01-01

Transactions on Pattern Languages of Programming (published)

doi.org

Automated UML Visualization of Software Ecosystems: Tracking Versions, Dependencies, and Security Updates

Vanessa Kan

M. P. Lnu

Solomon Berhe

C. El Kari

Marc Maynard

Foutse Khomh

2025-01-01

ANT/EDI40 (published)

doi.org

Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification

Yunzhen Feng

Elvis Dohmatob

Pu Yang

Francois Charton

Julia Kempe

Large Language Models (LLM) are increasingly trained on data generated by other LLM, either because generated text and images become part of… (see more) the pre-training corpus, or because synthetized data is used as a replacement for expensive human-annotation. This raises concerns about \emph{model collapse}, a drop in model performance when their training sets include generated data. Considering that it is easier for both humans and machines to tell between good and bad examples than to generate high-quality samples, we investigate the use of verification on synthesized data to prevent model collapse. We provide a theoretical characterization using Gaussian mixtures, linear classifiers, and linear verifiers to derive conditions with measurable proxies to assess whether the verifier can effectively select synthesized data that leads to optimal performance. We experiment with two practical tasks -- computing matrix eigenvalues with transformers and news summarization with LLMs -- which both exhibit model collapse when trained on generated data, and show that verifiers, even imperfect ones, can indeed be harnessed to prevent model collapse and that our proposed proxy measure strongly correlates with performance.

2025-01-01

ICLR (published)

doi.org

arxiv.org

Body size and intracranial volume interact with the structure of the central nervous system: A multi-center in vivo neuroimaging study

René Labounek

Monica T. Bondy

Amy L. Paulson

Sandrine Bédard

Mihael Abramovic

Eva Alonso‐Ortiz

Nicole Atcheson

Laura R. Barlow

Robert L. Barry

Markus Barth

Marco Battiston

Christian Büchel

Matthew D. Budde

Virginie Callot

Anna Combes

Benjamin De Leener

Maxime Descoteaux

Paulo Loureiro de Sousa

Marek Dostál

Julien Doyon … (see 74 more)

Adam Dvorak

Falk Eippert

Karla R. Epperson

Kevin S. Epperson

Patrick Freund

Jürgen Finsterbusch

Alexandru Foias

Michela Fratini

Issei Fukunaga

Claudia A. M. Gandini Wheeler-Kingshott

Giancarlo Germani

Guillaume Gilbert

Federico Giove

Francesco Grussu

Akifumi Hagiwara

Pierre-Gilles Henry

Tomáš Horák

Masaaki Hori

James Joers

Kouhei Kamiya

Haleh Karbasforoushan

Miloš Keřkovský

Ali Khatibi

Joo-won Kim

Nawal Kinany

Hagen H. Kitzler

Shannon Kolind

Yazhuo Kong

Petr Kudlička

Paul Kuntke

Nyoman D. Kurniawan

Slawomir Kusmia

Maria Marcella Lagana

Cornelia Laule

Christine S. W. Law

Csw Law

Tobias Leutritz

Yaou Liu

Sara Llufriu

Sean Mackey

Allan R. Martin

Eloy Martinez-Heras

Loan Mattera

Kristin P. O’Grady

Nico Papinutto

Daniel Papp

Deborah Pareto

Todd B. Parrish

Anna Pichiecchio

Ferran Prados

Àlex Rovira

Marc J. Ruitenberg

Rebecca S. Samson

Giovanni Savini

Maryam Seif

Alan C. Seifert

Alex K. Smith

Seth Aaron Smith

Zachary A. Smith

Elisabeth Solana

Yuichi Suzuki

George Tackley

Alexandra Tinnermann

Jan Valosek

Dimitri Van De Ville

Marios C. Yiannakas

Kenneth A. Weber

Nikolaus Weiskopf

Richard G. Wise

Patrik O. Wyss

Junqian Xu

Julien Cohen-Adad

Christophe Lenglet

Igor Nestrašil

2025-01-01

Imaging Neuroscience (published)

doi.org

Celo: Training Versatile Learned Optimizers on a Compute Diet

Learned optimization has emerged as a promising alternative to hand-crafted optimizers, with the potential to discover stronger learned upda… (see more)te rules that enable faster, hyperparameter-free training of neural networks. A critical element for practically useful learned optimizers, that can be used off-the-shelf after meta-training, is strong meta-generalization: the ability to apply the optimizers to new tasks. Recent state-of-the-art work in learned optimizers, VeLO (Metz et al., 2022), requires a large number of highly diverse meta-training tasks along with massive computational resources, 4000 TPU months, to achieve meta-generalization. This makes further improvements to such learned optimizers impractical. In this work, we identify several key elements in learned optimizer architectures and meta-training procedures that can lead to strong meta-generalization. We also propose evaluation metrics to reliably assess quantitative performance of an optimizer at scale on a set of evaluation tasks. Our proposed approach, Celo, makes a significant leap in improving the meta-generalization performance of learned optimizers and also outperforms tuned state-of-the-art optimizers on a diverse set of out-of-distribution tasks, despite being meta-trained for just 24 GPU hours.

2025-01-01

Trans. Mach. Learn. Res. (published)

openreview.net

Changer le regard des étudiants sur les métiers de la comptabilité : Les effets de la simulation de gestion

Guillaume Dumas

Yann QUÉMÉNER

La comptabilité véhicule souvent injustement, une image terne et ennuyeuse, auprès du grand public et des jeunes étudiants choisissant l… (see more)eur orientation. Dans cet article, nous questionnons l’effet de pratiques pédagogiques sur la perception par les étudiants, des soft skills attendues par les employeurs. Pour cela nous réalisons une quasi-expérimentation dans laquelle nous comparons les perceptions des étudiants selon que le cours ait été animé sous un format classique (application des connaissances par le biais d’exercices avec corrigé par l’enseignant) ou sous la forme d’une simulation de gestion (application des connaissances en vue de prendre des décisions et piloter une entreprise fictive). Les résultats de la recherche montrent qu’une simulation de gestion, plus que les travaux dirigés classiques, permettent aux primo-apprenants en comptabilité, d’avoir une meilleure perception des soft skills attendues par les praticiens et les recruteurs. Nos résultats rappellent l’importance de donner une représentation réaliste (éloignée des clichés) de la profession, afin de rendre les filières d’enseignement de la comptabilité plus attractives.

2025-01-01

Finance Contrôle Stratégie (published)

doi.org

Child- and Proxy-reported Differences in Patient-reported Outcome and Experience Measures in Pediatric Surgery: Systematic Review and Meta-analysis

Zanib Nafees

Siena O'Neill

Alexandra Dimmer

Elena Guadagno

Julia Ferreira

Nancy Mayo

Dan Poenaru

2025-01-01