Publications

Gistify! Codebase-Level Understanding via Runtime Execution
Hyunji Lee
Minseon Kim
Chinmay Singh
Matheus Pereira
Atharv Sonwane
Isadora White
Elias Stengel-Eskin
Mohit Bansal
Zhengyan Shi
Alessandro Sordoni
Marc-Alexandre Côté
Xingdi Yuan
Lucas Caccia
As coding agents are increasingly deployed in large codebases, the need to automatically design challenging, codebase-level evaluation is ce… (voir plus)ntral. We propose Gistify, a task where a coding LLM must create a single, minimal, self-contained file that can reproduce a specific functionality of a codebase. The coding LLM is given full access to a codebase along with a specific entrypoint (e.g., a python command), and the generated file must replicate the output of the same command ran under the full codebase, while containing only the essential components necessary to execute the provided command. Success on Gistify requires both structural understanding of the codebase, accurate modeling of its execution flow as well as the ability to produce potentially large code patches. Our findings show that current state-of-the-art models struggle to reliably solve Gistify tasks, especially ones with long executions traces.
2025-10-29
ArXiv (prépublication)
doi.org
arxiv.org
Neural signatures of associational cortex emerge in a goal-directed model of visual search
Motahareh Pourrahimi
Pouya Bashivan
2025-10-29
bioRxiv (prépublication)
doi.org
Multi-Representation Attention Framework for Underwater Bioacoustic Denoising and Recognition
Amine RAZIG
Youssef Soulaymani
Loubna Benabbou
Pierre Cauchy
2025-10-28
ArXiv (prépublication)
doi.org
arxiv.org
Scaling Latent Reasoning via Looped Language Models
Ruiming Zhu
Zixuan Wang
Kai Hua
Tianyu Zhang
Ziniu Li
Haoran Que
Boyi Wei
Zixin Wen
Fan Yin
He Xing
Li Li
Jiajun Shi
Kaijing Ma
Shanda Li
Taylor Kergan
Andrew C. Smith
Xin Qu
Mude Hui
Bohong Wu
Qiyang Min … (voir 13 de plus)
Hongzhi Huang
Xun Zhou
Wei Ye
Jiaheng Liu
Jian Yang 0030
Yunfeng Shi
Chenghua Lin
Enduo Zhao
Tianle Cai
Ge Zhang
Wenhao Huang
Yoshua Bengio
Jason K. Eshraghian
Modern LLMs are trained to"think"primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-trai… (voir plus)ning and under-leverages pre-training data. We present and open-source Ouro, named after the recursive Ouroboros, a family of pre-trained Looped Language Models (LoopLM) that instead build reasoning into the pre-training phase through (i) iterative computation in latent space, (ii) an entropy-regularized objective for learned depth allocation, and (iii) scaling to 7.7T tokens. Ouro 1.4B and 2.6B models enjoy superior performance that match the results of up to 12B SOTA LLMs across a wide range of benchmarks. Through controlled experiments, we show this advantage stems not from increased knowledge capacity, but from superior knowledge manipulation capabilities. We also show that LoopLM yields reasoning traces more aligned with final outputs than explicit CoT. We hope our results show the potential of LoopLM as a novel scaling direction in the reasoning era. Our model is available here: http://ouro-llm.github.io.
2025-10-28
ArXiv (prépublication)
doi.org
arxiv.org
Assessing Programming Task Difficulty for Efficient Evaluation of Large Language Models
Florian Tambon
Amin Nikanjam
Cyrine Zid
Foutse Khomh
Giuliano Antoniol
2025-10-27
ACM Transactions on Software Engineering and Methodology (publié)
doi.org
arxiv.org
Bridging Simulators with Conditional Optimal Transport
Justine Zeghal
Benjamin Remy
Yashar Hezaveh
François Lanusse
Laurence Perreault-Levasseur
2025-10-27
ArXiv (prépublication)
arxiv.org
arxiv.org
AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages
Kosei Uemura
Miaoran Zhang
David Ifeoluwa Adelani
2025-10-26
ArXiv (prépublication)
doi.org
arxiv.org
Quantitative MRI of the hippocampus reveals microstructural trajectories of aging and Alzheimer’s disease pathology
Alfie Wearn
Christine Tardif
Ilana R. Leppert
Giulia Baracchini
Colleen Hughes
Jennifer Tremblay‐Mercier
John C.S. Breitner
Judes Poirier
Sylvia Villeneuve
Boris C. Bernhardt
Gary R. Turner
R. Nathan Spreng
Sylvia Villeneuve
Judes Poirier
John C.S. Breitner
Sylvain Baillet
Andrée‐Ann Baril
Pierre Bellec
Véronique D. Bohbot
Danilo Bzdok … (voir 27 de plus)
M. Mallar Chakravarty
D. Louis Collins
Mahsa Dadar
Simon Ducharme
Alan C. Evans
Claudine Gauthier
Maiya R. Geddes
Rick Hoge
Yasser Ituria‐Medina
Gerhard Multhaup
Lisa Marie Munter
Alexa Pichet Binette
Natasha Rajah
Pedro Rosa‐Neto
Taylor W. Schmitz
Jean‐Paul Soucy
R. Nathan Spreng
Christine Tardif
Étienne Vachon‐Presseau
Christian Bocti
Maxime Descoteaux
Robert Laforce
Pierre Étienne
Serge Gauthier
Vasavan Nair
Jens C. Pruessner
Daniel Auld
Hippocampal atrophy, typically measured using volumetry, is a hallmark feature of both normal aging and Alzheimer’s disease (AD). However,… (voir plus) the earliest stages of atrophy manifest as microstructural changes in tissue composition rather than macroscopic volume loss. We conducted longitudinal in vivo mapping of hippocampal microstructure in healthy aging and incipient AD, highlighting demyelination, iron deposition, and changes in water content as markers of age and AD risk. A combination of macrostructural and microstructural measures provides a more comprehensive picture of brain health and disease, unlocking unique insights into the pathological state of brain tissue and the impact of AD at a point where therapeutic rescue of the tissue is most likely to be efficacious.
2025-10-26
Proceedings of the National Academy of Sciences (publié)
doi.org
deadtrees.earth — An open-access and interactive database for centimeter-scale aerial imagery to uncover global tree mortality dynamics
Clemens Mosig
Janusch Vajna-Jehle
Miguel D. Mahecha
Yan Cheng
Henrik Hartmann
David Montero
Samuli Junttila
Stéphanie Horion
Mirela Beloiu Schwenke
Michael J. Koontz
Khairul Nizam Abdul Maulud
Stephen Adu-Bredu
Djamil Al-Halbouni
Muhammad Ali
Matthew Allen
Jan Altman
Lot Amorós
Claudia Angiolini
Rasmus Astrup
Hassan Awada … (voir 80 de plus)
Caterina Barrasso
Harm Bartholomeus
Pieter S.A. Beck
Aurora Bozzini
Joshua Braun-Wimmer
Benjamin Brede
Fabio Marcelo Breunig
Stefano Brugnaro
Allan Buras
Vicente Burchard-Levine
Jesús Julio Camarero
Anna Candotti
Luka Capuder
Erik Carrieri
Mauro Centritto
Gherardo Chirici
Myriam Cloutier
Dhemerson Conciani
KC Cushman
James W. Dalling
Phuong D. Dao
Jan Dempewolf
Martin Denter
Marcel Dogotari
Ricardo Díaz-Delgado
Simon Ecke
Jana Eichel
Anette Eltner
André Fabbri
Maximilian Fabi
Fabian Fassnacht
Matheus Pinheiro Ferreira
Fabian Jörg Fischer
Julian Frey
Annett Frick
Jose Fuentes
Selina Ganz
Matteo Garbarino
Milton García
Matthias Gassilloud
Antonio Gazol
Guillermo Gea-Izquierdo
Kilian Gerberding
Marziye Ghasemi
Francesca Giannetti
Jeffrey Gillan
Roy Gonzalez
Carl Gosper
Terry Greene
Konrad Greinwald
Stuart Grieve
André Große-Stoltenberg
Jesus Aguirre Gutierrez
Anna Göritz
Peter Hajek
David Hedding
Jan Hempel
Stien Heremans
Melvin Hernández
Marco Heurich
Eija Honkavaara
Bernhard Höfle
Robert Jackisch
Tommaso Jucker
Jesse M. Kalwij
Sebastian Kepfer-Rojas
Pratima Khatri-Chhetri
Till Kleinebecker
Hans-Joachim Klemmt
Tomáš Klouček
Niko Koivumäki
Nagesh Kolagani
Jan Komárek
Kirill Korznikov
Bartłomiej Kraszewski
Stefan Kruse
Robert Krüger
Helga Kuechly
Ivan H.Y. Kwong
Étienne Laliberté
2025-10-23
Remote Sensing of Environment (publié)
doi.org
Deep-learning-based virtual screening of antibacterial compounds
Gabriele Scalia
Steven T. Rutherford
Ziqing Lu
Kerry R. Buchholz
Nicholas Skelton
Kangway Chuang
Nathaniel Diamant
Jan-Christian Hütter
Jerome-Maxim Luescher
Anh Miu
Jeff Blaney
Leo Gendelev
Elizabeth Skippington
Greg Zynda
Nia Dickson
Michał Koziarski
Yoshua Bengio
Aviv Regev
Man-Wah Tan
Tommaso Biancalani
2025-10-23
Nature Biotechnology (inconnu)
doi.org
Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds
Oscar Davis
Michael S. Albergo
Nicholas Matthew Boffi
Michael M. Bronstein
Avishek Bose
2025-10-23
ArXiv (prépublication)
doi.org
arxiv.org
REVE: A Foundation Model for EEG -- Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects
Yassine El Ouahidi
Jonathan Lys
Philipp Thölke
Nicolas Farrugia
Bastien Pasdeloup
Vincent Gripon
Karim Jerbi CoCo Lab
Giulia Lioi
2025-10-23
ArXiv (prépublication)
doi.org
arxiv.org