386 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Systèmes d'Elevage Méditerranéens et Tropicaux - Laboratoire de Recherche sur le Développement de l'ElevageFR7 papers
- Université Gustave EiffelFR7 papers
- Sorbonne UniversitéFR6 papers
- Laboratoire d'Informatique Gaspard-MongeFR5 papers
- Centre National de la Recherche ScientifiqueFR4 papers
- Technical University of MunichDE4 papers
- Imperial College LondonGB3 papers
- Nvidia (United States)US3 papers
- The University of Texas MD Anderson Cancer CenterUS3 papers
- Université Paris-SaclayFR3 papers
- University College LondonGB3 papers
- University Hospital of BernCH3 papers
45 papers
Verification of Dynamic Holographic Behavior in Identity Documents
Glen Pouliquen, Joseph Chazalon, Guillaume Chiron +2
This paper addresses the remote verification of the authenticity of Optically Variable Devices (commonly known as holograms) on identity documents. Typically placed over the cardho…
AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents
Laïla Elkoussy, Julien Perez
Tool-using LLM agents are usually evaluated by final-answer correctness or LLM judges. Neither captures how an answer was produced. In safety-critical settings, the procedure itsel…
HistoriQA-ThirdRepublic: Multi-Hop Question Answering Corpus for Historical Research, Parliamentary Debates from the French Third Republic (1870-1940)
Aurélien Pellet, Julien Perez, Marie Puren
We present HistoriQA-ThirdRepublic: a French-language dataset of multi-hop historical questions derived from parliamentary debates and newspapers of the French Third Republic. Desi…
SWE-QA: A Dataset and Benchmark for Complex Code Understanding
Laïla Elkoussy, Julien Perez
In this paper, we introduce SWE-QA, a text and code corpus aimed at benchmarking multi-hop code comprehension, addressing the gap between simplified evaluation tasks and the comple…
Self-Supervised Learning for Speaker Recognition: A study and review
Theo Lepage, Reda Dehak
Deep learning models trained in a supervised setting have revolutionized audio and speech processing. However, their performance inherently depends on the quantity of human-annotat…
Multiple outflows and delayed ejections revealed by early imaging of novae
Elias Aydi, John D. Monnier, Antoine Mérand +39
Novae are thermonuclear eruptions on accreting white dwarfs in interacting binaries. Although most of the accreted envelope is expelled, the mechanism -- impulsive ejection, multip…
Fast-VAT: Accelerating Cluster Tendency Visualization using Cython and Numba
MSR Avinash, Ismael Lachheb
Visual Assessment of Cluster Tendency (VAT) is a widely used unsupervised technique to assess the presence of cluster structure in unlabeled datasets. However, its standard impleme…
Cryptanalysis of a multivariate CCZ scheme
Alessio Caminata, Elisa Gorla, Madison Mabe +2
We consider the multivariate scheme Pesto, which was introduced by Calderini, Caminata, and Villa. In this scheme, the public polynomials are obtained by applying a CCZ transformat…
Büchi-Elgot-Trakhtenbrot Theorem for Higher-Dimensional Automata
Amazigh Amrane, Hugo Bazille, Emily Clement +3
In this paper we explore languages of higher-dimensional automata (HDAs) from an algebraic and logical point of view. Such languages are sets of finite width-bounded interval pomse…
Found in Translation: semantic approaches for enhancing AI interpretability in face verification
Miriam Doh, Caroline Mazini Rodrigues, N. Boutry +3
The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to…
Self-Supervised Frameworks for Speaker Verification via Bootstrapped Positive Sampling
Theo Lepage, Reda Dehak
Recent developments in Self-Supervised Learning (SSL) have demonstrated significant potential for Speaker Verification (SV), but closing the performance gap with supervised systems…
Quantum-Safe Hybrid Key Exchanges with KEM-Based Authentication
Christopher Battarbee, Christoph Striecks, Ludovic Perret +2
Authenticated Key Exchange (AKE) between any two entities is one of the most important security protocols available for securing our digital networks and infrastructures. In PQCryp…
Digital Humanities in the TIME-US Project: Richness and Contribution of Interdisciplinary Methods for Labour History
Marie Puren
In 2015, the Annales journal, traditionally open to interdisciplinary approaches in history, referred to 'the current historiographical moment [as] call [ing] for an experimentatio…
Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection
Theophile Stourbe, Victor Miara, Theo Lepage +1
This paper describes our submitted systems to the ASVspoof 5 Challenge Track 1: Speech Deepfake Detection - Open Condition, which consists of a stand-alone speech deepfake (bonafid…
Real-time, accurate, and open source upper-limb musculoskeletal analysis using a single RGBD camera
Amedeo Ceglia, Kael Facon, Mickaël Begon +1
Biomechanical biofeedback may enhance rehabilitation and provide clinicians with more objective task evaluation. These feedbacks often rely on expensive motion capture systems, whi…
InaGVAD : a Challenging French TV and Radio Corpus Annotated for Speech Activity Detection and Speaker Gender Segmentation
David Doukhan, Christine Maertens, William Le Personnic +2
InaGVAD is an audio corpus collected from 10 French radio and 18 TV channels categorized into 4 groups: generalist radio, music radio, news TV, and generalist TV. It contains 277 1…
Explaning with trees: interpreting CNNs using hierarchies
Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman
Challenges persist in providing interpretable explanations for neural network reasoning in explainable AI (xAI). Existing methods like Integrated Gradients produce noisy maps, and…
Towards Supervised Performance on Speaker Verification with Self-Supervised Learning by Leveraging Large-Scale ASR Models
Victor Miara, Theo Lepage, Reda Dehak
Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems rema…
Automatic Hardware Pragma Insertion in High-Level Synthesis: A Non-Linear Programming Approach
Stéphane Pouget, Louis-Noël Pouchet, Jason Cong
High-Level Synthesis enables the rapid prototyping of hardware accelerators, by combining a high-level description of the functional behavior of a kernel with a set of micro-archit…
Additive Margin in Contrastive Self-Supervised Frameworks to Learn Discriminative Speaker Representations
Theo Lepage, Reda Dehak
Self-Supervised Learning (SSL) frameworks became the standard for learning robust class representations by benefiting from large unlabeled datasets. For Speaker Verification (SV),…
Transforming gradient-based techniques into interpretable methods
Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman
The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels ex…
Neural Koopman prior for data assimilation
Anthony Frion, Lucas Drumetz, Mauro Dalla Mura +2
With the increasing availability of large scale datasets, computational power and tools like automatic differentiation and expressive neural network architectures, sequential data…
Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification
Theo Lepage, Reda Dehak
Most state-of-the-art self-supervised speaker verification systems rely on a contrastive-based objective function to learn speaker representations from unlabeled speech data. We ex…
Linear Object Detection in Document Images using Multiple Object Tracking
Philippe Bernet, Joseph Chazalon, Edwin Carlinet +2
Linear objects convey substantial information about document structure, but are challenging to detect accurately because of degradation (curved, erased) or decoration (doubled, das…