Publications

Ultrasound (US) is considered a key modality for the clinical assessment of hepatic steatosis (i.e., fatty liver) due to its noninvasiveness… (see more) and availability. Deep learning methods have attracted considerable interest in this field, as they are capable of learning patterns in a collection of images and achieve clinically comparable levels of accuracy in steatosis grading. However, variations in patient populations, acquisition protocols, equipment, and operator expertise across clinical sites can introduce domain shifts that reduce model performance when applied outside the original training setting. In response, unsupervised domain adaptation techniques are being investigated to address these shifts, allowing models to generalize more effectively across diverse clinical environments. In this work, we propose a test-time batch normalization (TTN) technique designed to handle domain shift, especially for changes in label distribution, by adapting selected features of batch normalization (BatchNorm) layers in a trained convolutional neural network model. This approach operates in an unsupervised manner, allowing robust adaptation to new distributions without access to label data. The method was evaluated on two abdominal US datasets collected at different institutions, assessing its capability in mitigating domain shift for hepatic steatosis classification. The proposed method reduced the mean absolute error in steatosis grading by 37% and improved the area under the receiver operating characteristic curves (AUC) for steatosis detection from 0.78 to 0.97, compared to nonadapted models. These findings demonstrate the potential of the proposed method to address domain shift in US-based hepatic steatosis diagnosis, minimizing risks associated with deploying trained models in various clinical settings.

2025-03-25

IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control (published)

doi.org

Collective Decision Making by Embodied Neural Agents

Nicolas Coucke

Mary Katherine Heinrich

Axel Cleeremans

Marco Dorigo

Guillaume Dumas

Collective decision making using simple social interactions has been studied in many types of multi-agent systems, including robot swarms an… (see more)d human social networks. However, existing multi-agent studies have rarely modeled the neural dynamics that underlie sensorimotor coordination in embodied biological agents. In this study, we investigated collective decisions that resulted from sensorimotor coordination among agents with simple neural dynamics. We equipped our agents with a model of minimal neural dynamics based on the coordination dynamics framework, and embedded them in an environment with a stimulus gradient. In our single-agent setup, the decision between two stimulus sources depends solely on the coordination of the agent's neural dynamics with its environment. In our multi-agent setup, that same decision also depends on the sensorimotor coordination between agents, via their simple social interactions. Our results show that the success of collective decisions depended on a balance of intra-agent, inter-agent, and agent-environment coupling, and we use these results to identify the influences of environmental factors on decision difficulty. More generally, our results demonstrate the impact of intra- and inter-brain coordination dynamics on collective behavior, can contribute to existing knowledge on the functional role of inter-agent synchrony, and are relevant to ongoing developments in neuro-AI and self-organized multi-agent systems.

2025-03-24

PNAS Nexus (published)

doi.org

arxiv.org

Data Visualization using Functional Data Analysis

Haozhe Chen

Andres Duque Correa

Guy Wolf

Kevin R. Moon

Data visualization via dimensionality reduction is an important tool in exploratory data analysis. However, when the data are noisy, many ex… (see more)isting methods fail to capture the underlying structure of the data. Furthermore, existing methods that can theoretically eliminate all noise are difficult to implement in high dimensions. Here we propose a new data visualization method called Functional Information Geometry (FIG) for dynamical processes that denoises the data by leveraging time information and mitigates the curse of dimensionality using approaches from functional data analysis. We experimentally demonstrate that FIG outperforms other methods in terms of capturing the true structure, hyperparameter robustness, and computational speed. We then use our method to visualize EEG brain measurements of sleep activity.

2025-03-24

SampTA/2025/Conference (poster)

doi.org

openreview.net

Extendable Planning via Multiscale Diffusion

Chang Chen

Hany Hamed

Doojin Baek

Taegu Kang

Yoshua Bengio

Sungjin Ahn

Long-horizon planning is crucial in complex environments, but diffusion-based planners like Diffuser are limited by the trajectory lengths o… (see more)bserved during training. This creates a dilemma: long trajectories are needed for effective planning, yet they degrade model performance. In this paper, we introduce this extendable long-horizon planning challenge and propose a two-phase solution. First, Progressive Trajectory Extension incrementally constructs longer trajectories through multi-round compositional stitching. Second, the Hierarchical Multiscale Diffuser enables efficient training and inference over long horizons by reasoning across temporal scales. To avoid the need for multiple separate models, we propose Adaptive Plan Pondering and the Recursive HM-Diffuser, which unify hierarchical planning within a single model. Experiments show our approach yields strong performance gains, advancing scalable and efficient decision-making over long-horizons.

2025-03-24

ArXiv (preprint)

doi.org

arxiv.org

Gemma 3 Technical Report

Gemma Team Aishwarya Kamath

Johan Ferret

Shreya Pathak

Nino Vieillard

Ramona Merhej

Sarah Perrin

Tatiana Matejovicova

Alexandre Ram'e

Morgane Rivière

Louis Rouillard

Thomas Mesnard

Geoffrey Cideron

Jean-Bastien Grill

Sabela Ramos

Edouard Yvinec

Michelle Casbon

Etienne Pot

Ivo Penchev

Gael Liu

Francesco Visin … (see 190 more)

Kathleen Kenealy

Lucas Beyer

Xiaohai Zhai

Anton Tsitsulin

Róbert Busa-Fekete

Alex Feng

Noveen Sachdeva

Benjamin Coleman

Yi Gao

Basil Mustafa

Iain Barr

Emilio Parisotto

David Tian

Matan Eyal

Colin Cherry

Jan-Thorsten Peter

Danila Sinopalnikov

Surya Bhupatiraju

Rishabh Agarwal

Mehran Kazemi

Dan Malkin

Ravin Kumar

David Vilar

Idan Brusilovsky

Jiaming Luo

Andreas Steiner

Abe Friesen

Abhanshu Sharma

Abheesht Sharma

Adi Mayrav Gilady

Adrian Goedeckemeyer

Alaa Saade

Alexander Kolesnikov

Alexei Bendebury

Alvin Abdagic

Amit Vadi

Andr'as Gyorgy

André Susano Pinto

Anil Das

Ankur Bapna

Antoine Miech

Antoine Yang

Antonia Paterson

Ashish Shenoy

Ayan Chakrabarti

Bilal Piot

Boxi Wu

Bobak Shahriari

Bryce Petrini

Charlie Chen

Charline Le Lan

Christopher A. Choquette-Choo

CJ Carey

Cormac Brick

Daniel Deutsch

Danielle Eisenbud

Dee Cattle

Derek Cheng

Dimitris Paparas

Divyashree Shivakumar Sreepathihalli

Doug Reid

Dustin Tran

Dustin Zelle

Eric Noland

Erwin Huizenga

Eugene Kharitonov

Frederick Liu

Gagik Amirkhanyan

Glenn Cameron

Hadi Hashemi

Hanna Klimczak-Pluci'nska

Harman Singh

Harsh Mehta

Harshal Tushar Lehri

Hussein Hazimeh

Ian Ballantyne

Idan Szpektor

Ivan Nardini

Jean Pouget-Abadie

Jetha Chan

Joe Stanton

J. Michael Wieting

Jonathan Lai

Jordi Orbay

Joe Fernandez

Joshua Newlan

Junsong Ji

Jyotinder Singh

Kat Black

Kathy Yu

Kevin Hui

Kiran N. Vodrahalli

Klaus Greff

Linhai Qiu

Marcella Valentine

Marina Coelho

Marvin Ritter

Matt Hoffman

Matthew Watson

Mayank Chaturvedi

Michael Moynihan

Min Ma

Nabila Babar

Natasha Noy

Nathan Byrd

Nick Roy

Nikola Momchev

Nilay Chauhan

Oskar Bunyan

Pankil Botarda

Paul Caron

Paul Kishan Rubenstein

Phil Culliton

Philipp Schmid

Pier Giuseppe Sessa

Pingmei Xu

Piotr Stańczyk

Pouya Dehghani Tafti

Rakesh Shivanna

Renjie Wu

Renke Pan

R. Rokni

Rob Willoughby

Rohith Vallu

Ryan Mullins

Sammy Jerome

Sara Smoot

Sertan Girgin

Shariq Iqbal

Shashir Reddy

Shruti Sheth

Siim Põder

Sijal Bhatnagar

S. Panyam

Sivan Eiger

Susan Zhang

Tianqi Liu

Trevor Yacovone

T. Liechty

Uday Kalra

Utku Evci

Vedant Misra

Vincent Roseberry

Vladimir Feinberg

Vlad Kolesnikov

Woohyun Han

Woosuk Kwon

X. T. Chen

Yinlam Chow

Yuvein Zhu

Zichuan Wei

Z. Egyed

Victor Cotruta

Minh Giang

Phoebe Kirk

Anand Rao

Jessica Lo

Erica Moreira

Luiz GUStavo Martins

Omar Sanseviero

Lucas Gonzalez

Zach Gleicher

Tris Brian Warkentin

Seyed Vahab Mirrokni

Evan Senter

Eli Collins

Joelle Barral

Zoubin Ghahramani

Raia Hadsell

Yossi Matias

D. Sculley

Slav Petrov

Noah Fiedel

Noam M. Shazeer

Oriol Vinyals

Jeffrey Dean

Demis Hassabis

Koray Kavukcuoglu

Clément Farabet

Elena Buchatskaya

Jean-Baptiste Alayrac

Rohan Anil

Dmitry Lepikhin

Sebastian Borgeaud

Olivier Bachem

Armand Joulin

Alek Andreev

Cassidy Hardin

Robert Dadashi

L'eonard Hussenot

We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters… (see more). This version introduces vision understanding abilities, a wider coverage of languages and longer context - at least 128K tokens. We also change the architecture of the model to reduce the KV-cache memory that tends to explode with long context. This is achieved by increasing the ratio of local to global attention layers, and keeping the span on local attention short. The Gemma 3 models are trained with distillation and achieve superior performance to Gemma 2 for both pre-trained and instruction finetuned versions. In particular, our novel post-training recipe significantly improves the math, chat, instruction-following and multilingual abilities, making Gemma3-4B-IT competitive with Gemma2-27B-IT and Gemma3-27B-IT comparable to Gemini-1.5-Pro across benchmarks. We release all our models to the community.

2025-03-24

ArXiv (preprint)

doi.org

arxiv.org

MeshUp: Multi-Target Mesh Deformation via Blended Score Distillation

Hyunwoo Kim

Itai Lang

Noam Aigerman

Thibault Groueix

Vladimir Kim

Rana Hanocka

We propose MeshUp, a technique that deforms a 3D mesh towards multiple target concepts, and intuitively controls the region where each conce… (see more)pt is expressed. Conveniently, the concepts can be defined as either text queries, e.g.,"a dog"and"a turtle,"or inspirational images, and the local regions can be selected as any number of vertices on the mesh. We can effectively control the influence of the concepts and mix them together using a novel score distillation approach, referred to as the Blended Score Distillation (BSD). BSD operates on each attention layer of the denoising U-Net of a diffusion model as it extracts and injects the per-objective activations into a unified denoising pipeline from which the deformation gradients are calculated. To localize the expression of these activations, we create a probabilistic Region of Interest (ROI) map on the surface of the mesh, and turn it into 3D-consistent masks that we use to control the expression of these activations. We demonstrate the effectiveness of BSD empirically and show that it can deform various meshes towards multiple objectives. Our project page is at https://threedle.github.io/MeshUp.

2025-03-24

2025 International Conference on 3D Vision (3DV) (published)

doi.org

arxiv.org

A scalable gene network model of regulatory dynamics in single cells

Paul Bertin

Joseph D Viviano

Alejandro Tejada-Lapuerta

Weixu Wang

Stefan Bauer

Fabian J. Theis

Yoshua Bengio