Publications

On the Challenges and Opportunities in Generative AI
Laura Manduchi
Clara Meister
Kushagra Pandey
Robert Bamler
Ryan Cotterell
Sina Däubener
Sophie Fellenz
Asja Fischer
Thomas Gärtner
Matthias Kirchler
Marius Kloft
Yingzhen Li
Christoph Lippert
Gerard de Melo
Eric Nalisnick
Björn Ommer
Rajesh Ranganath
Maja Rudolph
Karen Ullrich
Guy Van den Broeck … (voir 6 de plus)
Julia E Vogt
Yixin Wang
Florian Wenzel
Frank N. Wood
Stephan Mandt
Vincent Fortuin
2025-08-20
TMLR (accepté)
doi.org
openreview.net
Robustness of Neural Ratio and Posterior Estimators to Distributional Shifts for Population-Level Dark Matter Analysis in Strong Gravitational Lensing
Andreas Filipp
Yashar Hezaveh
Laurence Perreault-Levasseur
We investigate the robustness of Neural Ratio Estimators (NREs) and Neural Posterior Estimators (NPEs) to distributional shifts in the conte… (voir plus)xt of measuring the abundance of dark matter subhalos using strong gravitational lensing data. While these data-driven inference frameworks can be accurate on test data from the same distribution as the training sets, in real applications, it is expected that simulated training data and true observational data will differ in their distributions. We explore the behavior of a trained NRE and trained sequential NPEs to estimate the population-level parameters of dark matter subhalos from a large sample of images of strongly lensed galaxies with test data presenting distributional shifts within and beyond the bounds of the training distribution in the nuisance parameters (e.g., the background source morphology). While our results show that NREs and NPEs perform well when tested perfectly in distribution, they exhibit significant biases when confronted with slight deviations from the examples seen in the training distribution. This indicates the necessity for caution when applying NREs and NPEs to real astrophysical data, where high-dimensional underlying distributions are not perfectly known.
2025-08-19
The Astrophysical Journal (publié)
doi.org
arxiv.org
Causal single-cell RNA-seq simulation, in silico perturbation, and GRN inference benchmarking using GRouNdGAN-Toolkit
Yazdan Zinati
Amin Emad
2025-08-18
bioRxiv (prépublication)
doi.org
RadiSeq: a single- and bulk-cell whole-genome DNA sequencing simulator for radiation-damaged cell models
Felix Mathew
Luc Galarneau
J. Kildea
Objective To build and validate a simulation framework to perform single-cell and bulk-cell whole genome sequencing simulation of radiation-… (voir plus)exposed Monte Carlo cell models to assist radiation genomics studies. Approach Sequencing the genomes of radiation-damaged cells can provide useful insight into radiation action for radiobiology research. However, carrying out post-irradiation sequencing experiments can often be challenging, expensive, and time-consuming. Although computational simulations have the potential to provide solutions to these experimental challenges, and aid in designing optimal experiments, the absence of tools currently limits such application. Monte Carlo toolkits exist to simulate radiation exposures of cell models but there are no tools to simulate single- and bulk-cell sequencing of cell models containing radiation-damaged DNA. Therefore, we aimed to develop a Monte Carlo simulation framework to address this gap by designing a tool capable of simulating sequencing processes for radiation-damaged cells. Main Results We developed RadiSeq – a multi-threaded whole-genome DNA sequencing simulator written in C++. RadiSeq can be used to simulate Illumina sequencing of radiation-damaged cell models produced by Monte Carlo simulations. RadiSeq has been validated through comparative analysis, where simulated data were matched against experimentally obtained data, demonstrating reasonable agreement between the two. Additionally, it comes with numerous features designed to closely resemble actual whole-genome sequencing. RadiSeq is also highly customizable with a single input parameter file. Significance RadiSeq enables the research community to perform complex simulations of radiation-exposed DNA sequencing, supporting the optimization, planning, and validation of costly and time-intensive radiation biology experiments. This framework provides a powerful tool for advancing radiation genomics research.
2025-08-18
Physics in Medicine & Biology (publié)
doi.org
Field-Level Comparison and Robustness Analysis of Cosmological N-Body Simulations
Adrian E. Bayer
Francisco Villaescusa-navarro
Sammy Nasser Sharief
Romain Teyssier
Lehman H. Garrison
Laurence Perreault-Levasseur
Greg L. Bryan
Marco Gatti
E. Visbal
2025-08-17
The Astrophysical Journal (publié)
doi.org
arxiv.org
Proceedings of the OHBM Open Science Room 2024
Selma Lugtmeijer
Ju-Chi Yu
Xiangzhen Kong
Lune P Bellec
Janine D. Bijsterbosch
Elizabeth DuPre
Oscar Esteban
Ibrahim Faye
Seok-Jun Hong
Chuan-Peng Hu
Shella Keilholz
Chun-Chia Kung
Hyeong Hun Lee
Daniel Margulies
Cyril Pernet
Franco Pestilli
Jean-Baptiste Poline
Pradeep R. Raamana
Francesco Santini
Won Mok Shim … (voir 30 de plus)
Paul M. Thompson
Chao-Gan Yan
Niall W. Duncan
Nikhil Bhagwat
Peter Fox
Ana Van Gulick
David N. Kennedy
Gorana Pobric
Neda Sadeghi
Nick Souter
Sandeep Panta
Isabelle van der Velpen
Tonya White
Sina Mansour L.
Qing Wang
Povilas Karvelis
Anibal S. Heinsfeld
Yu-Fang Yang
Hong Ji Kim
Nur Shahidatul Nabila Binti Ibrahim
Stefano Moia
Wei Zhang
Jessica Haigh
Rose-Marie Kouwenhoven
Terra Hyun Lee
Hurshitha Vasudevan
Yuping Yang
Subapriya Suppiah
Yi-Ju Lee
Nils Muhlert
2025-08-17
Aperture Neuro (publié)
doi.org
Calm-Whisper: Reduce Whisper Hallucination On Non-Speech By Calming Crazy Heads Down
Yingzhi Wang
Anas Alhmoud
Saad Alsahly
Muhammad Alqurishi
Mirco Ravanaelli
2025-08-16
Interspeech 2025 (publié)
doi.org
arxiv.org
LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs
Pooneh Mousavi
Shubham Gupta
Yusuf Cem Sübakan
Mirco Ravanaelli
Foundation models based on large language models (LLMs) have shown great success in handling various tasks and modalities. However, adapting… (voir plus) these models for general-purpose audio-language tasks is challenging due to differences in acoustic environments and task variations. In this work, we introduce LiSTEN Learning Soft Token Embeddings for Neural Audio LLMs), a framework for adapting LLMs to speech and audio tasks. LiSTEN uses a dynamic prompt selection strategy with learnable key-value pairs, allowing the model to balance general and task-specific knowledge while avoiding overfitting in a multitask setting. Our approach reduces dependence on large-scale ASR or captioning datasets, achieves competitive performance with fewer trainable parameters, and simplifies training by using a single-stage process. Additionally, LiSTEN enhances interpretability by analyzing the diversity and overlap of selected prompts across different tasks.
2025-08-16
Interspeech 2025 (publié)
doi.org
arxiv.org
SandboxSocial: A Sandbox for Social Media Using Multimodal AI Agents
Maximilian Puelma Touzel
Sneheel Sarangi
Gayatri Krishnakumar
Busra Tugce Gurbuz
Austin Welch
Zachary Yang
Andreea Musulan
Hao Yu
Ethan Kosak-Hine
Tom Gibbs
Camille Thibault
Reihaneh Rabbany
Jean-François Godbout
Dan Zhao
Kellin Pelrine
The online information ecosystem enables influence campaigns of unprecedented scale and impact. We urgently need empirically grounded approa… (voir plus)ches to counter the growing threat of malicious campaigns, now amplified by generative AI. But, developing defenses in real-world settings is impractical. Social system simulations with agents modelled using Large Language Models (LLMs) are a promising alternative approach and a growing area of research. However, existing simulators lack features needed to capture the complex information-sharing dynamics of platform-based social networks. To bridge this gap, we present SandboxSocial, a new simulator that includes several key innovations, mainly: (1) a virtual social media platform (modelled as Mastodon and mirrored in an actual Mastodon server) that enables a realistic setting in which agents interact; (2) an adapter that uses real-world user data to create more grounded agents and social media content; and (3) multi-modal capabilities that enable our agents to interact using both text and images---just as humans do on social media. We make the simulator more useful to researchers by providing measurement and analysis tools that track simulation dynamics and compute evaluation metrics to compare experimental results.
2025-08-15
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (publié)
doi.org
Veracity: An Open-Source AI Fact-Checking System
Taylor Lynn Curtis
Maximilian Puelma Touzel
William Garneau
Manon Gruaz
Mike Pinder
Li Wei Wang
Sukanya Krishna
Luda Cohen
Jean-François Godbout
Reihaneh Rabbany
Kellin Pelrine
The proliferation of misinformation poses a significant threat to society, exacerbated by the capabilities of generative AI. This demo paper… (voir plus) introduces Veracity, an open-source AI system designed to empower individuals to combat misinformation through transparent and accessible fact-checking. Veracity leverages the synergy between Large Language Models (LLMs) and web retrieval agents to analyze user-submitted claims and provide grounded veracity assessments with intuitive explanations. Key features include multilingual support, numerical scoring of claim veracity, and an interactive interface inspired by familiar messaging applications. This paper will showcase Veracity's ability to not only detect misinformation but also explain its reasoning, fostering media literacy and promoting a more informed society.
2025-08-15
Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?
Yoshua Bengio
Michael Cohen
Damiano Fornasiere
Joumana Ghosn
Pietro Greiner
Matt MacDermott
Sören Mindermann
Adam Oberman
Jesse Richardson
Oliver Richardson
Marc-Antoine Rondeau
Pierre-Luc St-Charles
David Williams-King
The leading AI companies are increasingly focused on building generalist AI agents -- systems that can autonomously plan, act, and pursue go… (voir plus)als across almost all tasks that humans can perform. Despite how useful these systems might be, unchecked AI agency poses significant risks to public safety and security, ranging from misuse by malicious actors to a potentially irreversible loss of human control. We discuss how these risks arise from current AI training methods. Indeed, various scenarios and experiments have demonstrated the possibility of AI agents engaging in deception or pursuing goals that were not specified by human operators and that conflict with human interests, such as self-preservation. Following the precautionary principle, we see a strong need for safer, yet still useful, alternatives to the current agency-driven trajectory. Accordingly, we propose as a core building block for further advances the development of a non-agentic AI system that is trustworthy and safe by design, which we call Scientist AI. This system is designed to explain the world from observations, as opposed to taking actions in it to imitate or please humans. It comprises a world model that generates theories to explain data and a question-answering inference machine. Both components operate with an explicit notion of uncertainty to mitigate the risks of overconfident predictions. In light of these considerations, a Scientist AI could be used to assist human researchers in accelerating scientific progress, including in AI safety. In particular, our system can be employed as a guardrail against AI agents that might be created despite the risks involved. Ultimately, focusing on non-agentic AI may enable the benefits of AI innovation while avoiding the risks associated with the current trajectory. We hope these arguments will motivate researchers, developers, and policymakers to favor this safer path.
2025-08-14
SuperIntelligence - Robotics - Safety & Alignment (publié)
doi.org
arxiv.org
Deep learning reveals that multidimensional social status drives population variation in 11,875 US participant cohort
Justin Marotta
Shambhavi Aggarwal
Nicole Osayande
Karin Saltoun
Jakub Kopal
Avram J. Holmes
Sarah W. Yip
Danilo Bzdok
As an increasing realization, many behavioral relationships are interwoven with inherent variations in human populations. Presently, there i… (voir plus)s no clarity in the biomedical community on which sources of population variation are most dominant. The recent advent of population-scale cohorts like the Adolescent Brain Cognitive DevelopmentSM Study (ABCD Study®) are now offering unprecedented depth and width of phenotype profiling that potentially explains interfamily differences. Here, we leveraged a deep learning framework (conditional variational autoencoder) on the totality of the ABCD Study® phenome (8,902 candidate phenotypes in 11,875 participants) to identify and characterize major sources of population stratification. 80% of the top 5 sources of explanatory stratifications were driven by distinct combinations of 202 available socioeconomic status (SES) measures; each in conjunction with a unique set of non-overlapping social and environmental factors. Several sources of variation across this cohort flagged geographies marked by material poverty interlocked with mental health and behavioral correlates. Deprivation emerged in another top stratification in relation to urbanicity and its ties to immigrant and racial and ethnic minoritized groups. Conversely, two other major sources of population variation were both driven by indicators of privilege: one highlighted measures of access to educational opportunity and income tied to healthy home environments and good behavior, the other profiled individuals of European ancestry leading advantaged lifestyles in desirable neighborhoods in terms of location and air quality. Overall, the disclosed social stratifications underscore the importance of treating SES as a multidimensional construct and recognizing its ties into social determinants of health.
2025-08-12
Public Library of Science ONE (publié)
doi.org