output
20062025
most citedDynamical Variational Autoencoders: A Comprehensive Review

169 citations

13 papers

cs.LG2025

How Foundational are Foundation Models for Time Series Forecasting?

Nouha Karaouli, Denis Coquenet, Elisa Fromont +2

Foundation Models are designed to serve as versatile embedding machines, with strong zero shot capabilities and superior generalization performance when fine-tuned on diverse downs…

cs.LG2025

Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting

Nouha Karaouli, Denis Coquenet, Elisa Fromont +2

While Time Series Foundation Models (TSFMs) excel in zero-shot tasks, their behavior under continual fine tuning is poorly understood. We present the first systematic study of cata…

stat.AP2024★ 1 cited

A statistical procedure to assist dysgraphia detection through dynamic modelling of handwriting

Yunjiao Lu, Jean-Charles Quinton, Caroline Jolly +1

Dysgraphia is a neurodevelopmental condition in which children encounter difficulties in handwriting. Dysgraphia is not a disorder per se, but is secondary to neurodevelopmental di…

q-bio.NC2024

Psychology of Artificial Intelligence: Epistemological Markers of the Cognitive Analysis of Neural Networks

Michael Pichat

What is the "nature" of the cognitive processes and contents of an artificial neural network? In other words, how does an artificial intelligence fundamentally "think," and in what…

physics.bio-ph2022★ 4 cited

Fish evacuate smoothly respecting a social bubble

R. Larrieu, P. Moreau, C. Graff +2

Crowd movements are observed among different species and on different scales, from insects to mammals, as well as in non-cognitive systems, such as motile cells. When forced to esc…

cs.SD2021★ 4 cited

Learning robust speech representation with an articulatory-regularized variational autoencoder

Marc-Antoine Georges, Laurent Girin, Jean-Luc Schwartz +1

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representati…

cs.LG2020★ 169 cited

Dynamical Variational Autoencoders: A Comprehensive Review

Laurent Girin, Simon Leglaive, Xiaoyu Bie +3

Variational autoencoders (VAEs) are powerful deep generative models widely used to represent high-dimensional complex data through a low-dimensional latent space learned in an unsu…

cs.CY2019★ 13 cited

The Dynamics of Handwriting Improves the Automated Diagnosis of Dysgraphia

Konrad Zolna, Thibault Asselborn, Caroline Jolly +4

Handwriting disorder (termed dysgraphia) is a far from a singular problem as nearly 8.6% of the population in France is considered dysgraphic. Moreover, research highlights the fun…

q-bio.NC2015★ 28 cited

The influence of infant-directed speech on 12-month-olds' intersensory perception of fluent speech

Claudia Kubicek, Judit Gervain, Anne Hillairet De Boisferon +3

The present study examined whether infant-directed (ID) speech facilitates intersensory matching of audio--visual fluent speech in 12-month-old infants. German-learning infantsâ au…

physics.med-ph2007★ 4 cited

Tongue Liminary Threshold Identification to Electrotactile Stimulation

Fabien Robineau, Nicolas Vuillerme, Jean-Pierre Orliaguet +1

Many applications use electrostimulation of the human skin to provide tactile sensation. The effect of electrotactile stimulations were studied on a 6x6 matrix of tactile electrode…

q-bio.NC2007★ 2 cited

Biomimetic Space-Variant Sampling in a Vision Prosthesis Improves the User's Skill in a Localization Task

B. Durette, L. Gamond, Sylvain Hanneton +2

In this experiment, we test the hypothesis of whether a 'retina-like' space variant sampling pattern can improve the efficiency of a visual prosthesis. Subjects wearing a visuo-aud…

physics.med-ph2007★ 34 cited

Guiding the surgical gesture using an electro-tactile stimulus array on the tongue: A feasibility study

Fabien Robineau, Frédéric Boy, Jean-Pierre Orliaguet +2

Under conventional "open-" surgery, the physician has to take care of the patient, interact with other clinicians and check several monitoring devices. Nowadays, the Computer Assis…

physics.med-ph2006★ 3 cited

Control of Surgical Gesture under Lingual Electro-Tactile Stimulation

Fabien Robineau, Frédéric Boy, Jean-Pierre Orliaguet +3

Performing minimal-invasive surgical punctures require guiding a needle toward an intracorporeal clinically-defined target. As this technique does not involve cutting the body open…