Publications

Analysis of PDEs

Learning features from Newton's algorithm: a way to accelerate nonlinear parametrized PDE solvers

It is well known that Newton's method converges faster when the initial guess is closer to a root of a system of nonlinear equations. In this paper, a two-stage Newton initial guess strategy is proposed by learning features from a parameter-space…

Rémy Vallot, Florian de Vuyst, Thibault Dairay, Mathilde Mougeot

Fluid mechanics

Mixing induced by Faraday surface waves

We investigate how surface waves enhance mixing across the interface between two miscible fluids with a small density contrast. Imposing a vertical, time-periodic acceleration, we excite Faraday waves both experimentally and numerically. In systems…

Andrés Castillo-Castellanos, Benoît-Joseph Gréa, Antoine Briard, Louis Gostiaux

Artificial Intelligence

Efficient Neural-Network-Based High-Resolution Radiative Transfer for CO₂ Retrieval, and Application to Interferometric Sensing

Studying climate change requires reducing uncertainties in CO2 and CH4 emission estimates to better distinguish anthropogenic from natural sources, which motivates spaceborne measurements with improved revisit frequency and spatial coverage. In this…

Jordan Lontsi Tedongmo, Yann Ferrec, Laurence Croizé, Pablo Musé, Gabriele Facciolo, Andrés Almansa

Image Processing

Theatre Chapbooks At Scale: A Statistical Comparative Analysis of Typography

We propose a statistical methodology that quantifies the similarity of typefaces between printed historical books. This provides a tool that accelerates philological analysis. Using character prototypes derived from clustering and aligning…

Diego Belzarena, Seginus Mowlavi, Paula Casariego Castiñeira, Alejandra Ulla Lorenzo, Gregory Randall, Jean-Michel Morel

International Conference on Document Analysis and Recognition - 2026

Image Processing

When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents

Optical Character Recognition (OCR) is a key component in the digitization of historical archives. Recently, Vision-Language Models (VLMs) have emerged as strong alternatives to traditional OCR systems, achieving state-of-the-art performance on…

Marina Gardella, Camilo Mariño, Diego Belzarena, Ignacio Ramírez, Gregory Randall, Jean-Michel Morel

Engineering Sciences

AI-driven real-time carbon footprint tracking and autonomous reduction for sustainable enterprises

Current practice in enterprise carbon reporting is heavily dependent on periodic emissions inventories and disconnected data streams. As a result, drivers of emissions are not detected quickly enough to enable responsive action. Here we build and…

Yuan Chai, Haytham F Isleem, Pawan Kumar, Ghanshyam G Tejani, David Bassir

Energy Strategy Reviews - 2026

Machine Learning

Unbiased Open World Regularization for Fair Self-Supervised Learning

Despite recent advances, self-supervised learning (SSL) models and Joint-Embedding Predictive Architectures (JEPAs) remain susceptible to learning spurious biases in the dataset. These techniques rely on regularization, which prevents representation…

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

Signal and Image processing

Detecting Moving Vehicles on Sentinel-2 Imagery Using Semi-Automatic Labeling From S2A/S2C Tandem Phase

During the commissioning phase of ESA’s Sentinel-2C, tandem images with Sentinel-2A were acquired with a delay of 30 seconds. We present a novel, automated method for labeling moving vehicles in Sentinel-2 images, leveraging the temporal offset…

Guillaume Buthmann, Florentin Poucin, Jérémy Anger

XXV ISPRS Congress 2026 - 2026

Machine Learning

Deep Generative Models for Complex Multi-component Industrial System Generation

This thesis studies deep generative modeling for constrained multi-component industrial design, using tire architecture generation as a representative case study. The core difficulty is not only to generate plausible components, but to produce…

Fouad Oubari

Machine Learning

Synthetic data for open medical research: current challenges and perspectives

Open science practices have many advocated benefits. At their core is the sharing of open data, especially open research data. Although their value is widely recognized, such data are rarely available in the healthcare domain. One of the main…

Rémy Chapelle, Bruno Falissard, Mohammed Sedki