180 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Université Paris-SaclayFR185 papers
- Centre National de la Recherche ScientifiqueFR119 papers
- Institut national de recherche en sciences et technologies du numériqueFR29 papers
- Laboratoire Interdisciplinaire de PhysiqueFR26 papers
- Sorbonne UniversitéFR20 papers
- Centre Inria de SaclayFR17 papers
- CentraleSupélecFR15 papers
- Local Initiatives Support CorporationUS15 papers
- Université Paris CitéFR15 papers
- Universidad Complutense de MadridES14 papers
- École Normale Supérieure - PSLFR11 papers
- Gleason (United States)US10 papers
36 papers · 1 filter
Stylized Meta-Album: Group-bias injection with style transfer to study robustness against distribution shifts
Romain Mussard, Aurélien Gauffre, Ihsan Ullah +4
We introduce Stylized Meta-Album (SMA), a new image classification meta-dataset comprising 24 datasets (12 content datasets, and 12 stylized datasets), designed to advance studies…
Language-Independent Sentiment Labelling with Distant Supervision: A Case Study for English, Sepedi and Setswana
Koena Ronny Mabokela, Tim Schlippe, Mpho Raborife +1
Sentiment analysis is a helpful task to automatically analyse opinions and emotions on various topics in areas such as AI for Social Good, AI in Education or marketing. While many…
Relativistic Maxwell-Bloch Equations with Applications to Astrophysics
Ningyan Fang, Victor Botez, Fereshteh Rajabi +1
We derive relativistic Maxwell-Bloch equations for potential applications in astronomical environments, where various radiative processes are known to occur, including the maser ac…
PRIVET: PRoximIty leakage detection Via Extreme value Theory
Antoine Szatkownik, Aurélien Decelle, Beatriz Seoane +7
Deep generative models are often trained on sensitive data, such as genetic sequences, health data, or more broadly, any copyrighted, licensed or protected content. This raises cri…
AMStraMGRAM: Adaptive Multi-cutoff Strategy Modification for ANaGRAM
Nilo Schwencke, Cyriaque Rousselot, Alena Shilova +1
Recent works have shown that natural gradient methods can significantly outperform standard optimizers when training physics-informed neural networks (PINNs). In this paper, we ana…
Formalizing Style in Personal Narratives
Gustave Cortal, Alain Finkel
Personal narratives are stories authors construct to make meaning of their experiences. Style, the distinctive way authors use language to express themselves, is fundamental to how…
The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound
Clément Morand, Anne-Laure Ligozat, Aurélie Névéol
Recent Machine Learning (ML) approaches have shown increased performance on benchmarks at the cost of escalating compute demands. Hardware, algorithmic and carbon optimizations hav…
Designing and Evaluating AI Margin Notes in Document Reader Software
Nikhita Joshi, Daniel Vogel
AI capabilities for document reader software are usually presented in separate chat interfaces. We explore integrating AI into document comments, a concept we formalize as AI margi…
Metamorphic Testing of Multimodal Human Trajectory Prediction
Helge Spieker, Nadjib Lazaar, Arnaud Gotlieb +1
Context: Predicting human trajectories is crucial for the safety and reliability of autonomous systems, such as automated vehicles and mobile robots. However, rigorously testing th…
Neural Field Turing Machine: A Differentiable Spatial Computer
Akash Malhotra, Nacéra Seghouani
We introduce the Neural Field Turing Machine (NFTM), a differentiable architecture that unifies symbolic computation, physical simulation, and perceptual inference within continuou…
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption
Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite +3
Causal machine learning has the potential to revolutionize decision-making by combining the predictive power of machine learning algorithms with the theory of causal inference. How…
9th Workshop on Sign Language Translation and Avatar Technologies (SLTAT 2025)
Fabrizio Nunnari, Cristina Luna Jiménez, Rosalee Wolfe +5
The Sign Language Translation and Avatar Technology (SLTAT) workshops continue a series of gatherings to share recent advances in improving deaf / human communication through non-i…
Reframing Pattern: A Comprehensive Approach to a Composite Visual Variable
Tingying He, Jason Dykes, Petra Isenberg +1
We present a new comprehensive theory for explaining, exploring, and using pattern as a visual variable in visualization. Although patterns have long been used for data encoding an…
Vehicular Cloud Computing: A cost-effective alternative to Edge Computing in 5G networks
Rosario Patanè, Nadjib Achir, Andrea Araldo +1
Edge Computing (EC) is a computational paradigm that involves deploying resources such as CPUs and GPUs near end-users, enabling low-latency applications like augmented reality and…
Combining Human-centred Explainability and Explainable AI
Janin Koch, Vitor Fortes Rey
This position paper looks at differences between the current understandings of human-centered explainability and explainability AI. We discuss current ideas in both fields, as well…
Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog
Lautaro Estienne, Gabriel Ben Zenou, Nona Naderi +2
As AI systems take on collaborative roles, they must reason about shared goals and beliefs-not just generate fluent language. The Rational Speech Act (RSA) framework offers a princ…
A Design Space for Visualization Transitions of 3D Spatial Data in Hybrid AR-Desktop Environments
Yucheng Lu, Tobias Rau, Benjamin Lee +4
We present a design space for animated transitions of the appearance of 3D spatial datasets in a hybrid Augmented Reality (AR)-desktop context. Such hybrid interfaces combine both…
A Hierarchical Deep Learning Approach for Minority Instrument Detection
Dylan Sechet, Francesca Bugiotti, Matthieu Kowalski +2
Identifying instrument activities within audio excerpts is vital in music information retrieval, with significant implications for music cataloging and discovery. Prior deep learni…
BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models
Ludovic Arnould, Salim Khazem, Hugues Ali Mehenni
Visual Language Models (VLMs) are now sufficiently advanced to support a broad range of applications, including answering complex visual questions, and are increasingly expected to…
StaQ: a Finite Memory Approach to Discrete Action Policy Mirror Descent
Alex Davey, Alena Shilova, Brahim Driss +1
In Reinforcement Learning (RL), regularization with a Kullback-Leibler divergence that penalizes large deviations between successive policies has emerged as a popular tool both in…
Fusion of heterogeneous data for robust degradation prognostics
Edgar Jaber, Emmanuel Remy, Vincent Chabridon +2
Assessing the degradation state of an industrial asset first requires evaluating its current condition and then to project the forecast model trajectory to a predefined prognostic…
New bounds for proper -conflict-free colourings
Quentin Chuet, Tianjiao Dai, Qiancheng Ouyang +1
A proper -colouring of a graph is called -conflict-free if every vertex has at least colours appearing exactly once in its neighbourhood.…
Physics-based super-resolved simulation of 3D elastic wave propagation adopting scalable Diffusion Transformer
Hugo Gabrielidis, Filippo Gatti, Stéphane Vialle
In this study, we develop a Diffusion Transformer (referred as to DiT1D) for synthesizing realistic earthquake time histories. The DiT1D generates realistic broadband accelerograms…
Cutwidth Bounds via Vertex Partitions
Antoine Amarilli, Benoît Groz
We study the cutwidth measure on graphs and ways to bound the cutwidth of a graph by partitioning its vertices. We consider bounds expressed as a function of two quantities: on the…