Publications

Machine Learning

Beyond Gaussian Worlds: Latent Geometry Matters for JEPAs

Recent Joint-Embedding Predictive Architectures (JEPAs) prevent representation collapse by constraining learned representations to follow a prescribed target distribution, such as an isotropic Gaussian or the uniform distribution on a hypersphere…

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

Computation and Language

Named Entity-Driven Graph Smoothing to Enhance Pretrained Document Embeddings in Clustering Tasks

Named Entity Recognition (NER) extracts structured semantic elements, such as persons, organizations, or biomedical concepts, that enhance document understanding. Rather than replacing pretrained document embeddings, we refine them by injecting…

Imed Keraghel, Mohamed Nadif

SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval - 2026

Engineering Sciences

Contribution of AI and Machine Learning in the Optimization of Ultrasensitive Biosensors: Review

Artificial intelligence (AI) and machine learning (ML) are reshaping the design, fabrication, and deployment of ultrasensitive biosensors by enabling data-driven optimization across the entire sensing pipeline. This review examines how ML assisted…

David Bassir, Muhammad Awais, Ata Jahangir Moshayedi

MATEC Web of Conferences - 2026

Geography

Optimal transport for primary care planning

This paper proposes a new model based on optimal transport theory that provides both a local and global measure of access to primary care. We extend a previously introduced OT-based spatial heterogeneity index designed to analyse spatial disparities…

Souleymane Kane Diallo, Joseph Touzet, Xavier Bacon

Engineering Sciences

YOLOv8-EVdet: An emergency vehicle detection method for autonomous vehicles

This work presents a deep-learning based approach for emergency vehicle detection and classification for various driving conditions. Conventional vision-based methods often struggle with poor lighting, motion blur, and occlusions caused by…

Petros Loukas, David Bassir, Angelos Amanatiadis

International Journal of Advanced Robotic Systems - 2026

Machine Learning

Towards stable and reliable neural networks for multi-image restoration problems

The restoration of images and videos from degraded multi-frame observations is a fundamental challenge in computer vision.While deep learning has significantly advanced this field, transitioning these models to practical, safety-critical deployments…

Zhe Zheng

Sensory Organs

SPONTANEOUS RELEASE OF AN EPIRETINAL MEMBRANE IN AN ADULT PATIENT WITH STARGARDT DISEASE-A CASE REPORT

Purpose: To report an unusual episode of formation and spontaneous release of a thickened hyaloid and dense epiretinal membrane (ERM) complicating Stargardt disease. Methods: Case report. Results: We report the case of a 40-year-old woman who was…

Aliénor Vienne-Jumeau, Raphael Atia, Isabelle Audo, Michel Paques, Sarah Mrejen

RETINAL Cases & Brief Reports - 2026

Signal and Image processing

Structured Handwritten Form Synthesis via Unsupervised Template Recovery and Field-Level Segmentation

Natalia Bottaioli, Yanhao Li, Thomas Gorges, Solène Tarride, Vincent Christlein, Gabriele Facciolo, Jean-Michel Morel

International Workshop on Document Analysis Systems - 2026

Life Sciences

Fog computing and internet of things technology enabled with artificial intelligence for healthcare

Philippe Ea

Advances in Fog Computing and the Internet of Things for Smart Healthcare - 2026

Other

Air-stable subsurface two-dimensional hole gas with strong spin-orbit interaction in single layer Pt on Ge

Two-dimensional hole gases (2DHGs) offer enhanced spin-orbit coupling and correlations, making them attractive for spintronic and quantum devices. Yet, most realizations require complex epitaxial structures and protective encapsulation, limiting…

Dan Wang, Thomas Pierron, Etienne Barre, Stephane Pons, Dimitri Roditchev, Marie D’angelo, François Debontridder, Marie Hervé, Tristan Cren, Charles Menil, Benoit Fauqué, Nicolas Bergeal, Sergio Vlaic

Nano Letters - 2026