38 citations
- Cyril de Runz4 profiles5 · h 13
- Ben Crulis2 profiles4 · h 2
- Barthélémy Serres3 · h 5
- Gilles Venturini3 · h 1
- V. Peralta3 · h 12
- Céline Poudat2 profiles2 · h 8
- Faten El Outa2 profiles2 · h 4
- Panos Vassiliadis2 profiles2 · h 45
- Patrick Marcel2 · h 19
- Alexandre Chanson1 · h 5
- Béatrice Bouchou-Markhoff1 · h 11
- Carlos Aguilar1 · h 3
- Centre National de la Recherche ScientifiqueFR5 papers
- Laboratoire d'Informatique Fondamentale et Appliquée de ToursFR4 papers
- Université Côte d'AzurFR3 papers
- Laboratoire Cognition, Langues, Langage, ErgonomieFR2 papers
- Laboratoire Jean-Alexandre DieudonnéFR2 papers
- University of IoanninaGR2 papers
- 3D Technology Laboratories (United States)US1 paper
- Centre de Recherche en Neurosciences de LyonFR1 paper
- Centre de Recherche en Sciences et Technologies de l'Information et de la CommunicationFR1 paper
- CERES - Centre d'expérimentation en méthodes numériques pour les recherches en sciences humaines et sociales1 paper
- COPE Health SolutionsUS1 paper
- Genomic Vision (France)FR1 paper
16 papers
Ternarization of Vision Language Models for use on edge devices
Ben Crulis, Cyril De Runz, Barthelemy Serres +1
We propose a process to compress a pre-trained Vision Language Model into a ternary version of itself instead of training a ternary model from scratch. A new initialization scheme…
Gain modulation of actions selection without synaptic relearning
Elif Köksal-Ersöz, Pascal Chossat, Frédéric Lavigne
Adaptation of behavior requires the brain to change goals in a changing environment. Synaptic learning has demonstrated its effectiveness in changing the probability of selecting a…
Talking to oneself in CMC: a study of self replies in Wikipedia talk pages
Ludovic Tanguy, Céline Poudat, Lydia-Mai Ho-Dac
This study proposes a qualitative analysis of self replies in Wikipedia talk pages, more precisely when the first two messages of a discussion are written by the same user. This sp…
Few-shot target-driven instance detection based on open-vocabulary object detection models
Ben Crulis, Barthelemy Serres, Cyril De Runz +1
Current large open vision models could be useful for one and few-shot object recognition. Nevertheless, gradient-based re-training solutions are costly. On the other hand, open-voc…
An experimental comparative study of backpropagation and alternatives for training binary neural networks for image classification
Ben Crulis, Barthelemy Serres, Cyril de Runz +1
Current artificial neural networks are trained with parameters encoded as floating point numbers that occupy lots of memory space at inference time. Due to the increase in the size…
Message du troisi{è}me type : irruption d'un tiers dans un dialogue en ligne
Ludovic Tanguy, Céline Poudat, Lydia-Mai Ho-Dac
Our study focuses on Wikipedia talk pages, from a global perspective analyzing contributors' behaviors in online interactions. Using a corpus comprising all Wikipedia talk pages in…