Publications

Artificial Intelligence

Beyond ReLU: Bifurcation, Oversmoothing, and Topological Priors

Graph Neural Networks (GNNs) learn node representations through iterative network-based message-passing. While powerful, deep GNNs suffer from oversmoothing, where node features converge to a homogeneous, non-informative state. We re-frame this…

Erkan Turan, Gaspard Abel, Maysam Behmanesh, Emery Pierson, Maks Ovsjanikov

ICML 2026 - International Conference on Machine Learning - 2026

Computer Vision and Pattern Recognition

Generalization Limits in Vehicle Re-Identification

Vehicle re-identification focuses on retrieving images of the same vehicle from a gallery given a query image. Upon closer inspection of commonly used datasets, we observe that vehicles with few visual differences-e.g., the same make, model, and…

Anis Yassine Ben Mabrouk, Antoine Tadros, Rafael Grompone von Gioi, Gabriele Facciolo, Axel Davy, Rodrigo Verschae

Signal and Image processing

Dark Signal Non-Uniformity for Source Camera Identification

Source camera identification is the task of determining the camera that captured an image. This is often performed using the photo response non-uniformity (PRNU) as the camera fingerprint. However, there is another sensor non-uniformity: the dark…

Julieta Umpierrez, Marina Gardella, Rafael Grompone von Gioi, Pablo Musé, Jean-Michel Morel

14th International Workshop on Biometrics and Forensics - 2026

Machine Learning

SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings

A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified isotropic Gaussian embeddings as optimal for minimizing downstream…

Léo Nicollier, Max Dunitz, Marc Pic, Pablo Musé, Enric Meinhardt-Llopis, Gabriele Facciolo

Trading and Market Microstructure

Machine learning approaches for market manipulation detection insurveillance systems

This thesis explores the use of machine learning for detecting market manipulation, in collaboration with the French financial regulator (Autorité des Marchés Financiers). Detecting manipulation poses unique challenges, including noisy high…

Anne Zhao

Image Processing

Pushbroom Satellite Source Identification Using PRNU: A Sentinel-2 Application

In this work, we take a step toward robust source identification for pushbroom satellite detectors by addressing source detector attribution in satellite imagery using Photo-Response Non-Uniformity (PRNU). As natural camera-based methods do not…

Matthieu Serfaty, Marina Gardella, Quentin Bammey, Rafael Grompone von Gioi, Carlo de Franchis

14th International Workshop on Biometrics and Forensics - 2026

Optimization and Control

GLOBe: A Modular Global Optimization library

Open-source libraries are have a catalytic role in research pipelines, where new methods must be compared against up-to-date baselines. We present the GLobal Optimization Benchmark (GLOBe) modular Python library that unifies classical and recent…

Gaëtan Serré, Argyris Kalogeratos, Nicolas Vayatis

Machine Learning

Bayesian Latent Space Models for Graphs Are Misspecified: Toward Robust Inference via Generalized Posteriors

Bayesian latent space models offer a principled approach to network representation, but rely on correct specification of both geometry and link function. Real-world networks often violate these assumptions, exhibiting geometric mismatch and…

Aldric Labarthe

Statistics

A Ranking Approach to Global Optimization

In this paper, we consider the problem of maximizing an unknown and potentially nonconvex function f over a compact and convex set X ⊂ R^d using as few observations f (x) as possible. We observe that the optimization of the function f essentially…

Cédric Malherbe, Gaëtan Serré, Argyris Kalogeratos, Nicolas Vayatis

Physics

Quantum approach for electrical system maintenance scheduling problem

Maintenance scheduling is essential to ensure the reliability of power transmission systems while limiting operational risk and respecting technical and resource constraints. Increasing system complexity due to asset aging and renewable integration…

Qinyan Zhou, Djahou N Tognon, Sofiane Chalal, Noureddine Henka, Sami Tazi, Fikri Hafid, Titouan Carette