Réunion


Self-Supervised Visual Learning: Methods, Applications and Challenges

Date : 15 Octobre 2026
Horaire : 09h00 - 17h30
Lieu : LIPADE, Université Paris Cité, 45 rue des Saints-Pères 75 006 Paris
Axes scientifiques :
  • Apprentissage machine
Organisateurs :
  • - Céline Teulière (IP)
  • - Arthur Aubret (Frankfurt Institute for Advanced Studies)

Nous vous rappelons que, afin de garantir l'accès de tous les inscrits aux salles de réunion, l'inscription aux réunions est gratuite mais obligatoire.

Inscriptions

22 personnes membres du GdR IASIS, et 21 personnes non membres du GdR, sont inscrits à cette réunion.

Capacité de la salle : 45 personnes. Nombre d'inscrits en présentiel : 32 ; Nombre d'inscrits en distanciel : 11
13 Places restantes

Annonce

Les demandes de prise en charge de missions par le GdR sont à formuler avant le 30 septembre.

La cellule gestion du GdR est fermée du 20 juillet au 5 septembre.

Présentation

Over the past six years, Self-Supervised Learning (SSL) has driven major advances in computer vision.
These methods have enabled new possibilities across a wide range of domains, including robotics, industrial applications, biological applications, and video generation. This workshop aims to bring together the regional community interested in SSL to review recent progress and discuss its current limitations. Despite impressive successes, SSL approaches remain highly data-hungry, often struggle to generalize to out-of-distribution tasks, and raise ethical concerns. To foster discussion around these challenges, the workshop will feature talks from established keynote speakers alongside presentations from junior researchers. The event offers an opportunity to identify promising research directions and encourage new collaborations within the community.

The topics include (not limited):

  • Self-supervised learning
  • Generative models
  • Multi-modal models
  • Industrial or interdisciplinary applications
  • Embodied and active learning

Invited speakers (confirmed)

  • Diane Larlus (Naver labs)
  • Oriane Siméoni (Meta-FAIR)
  • Jean Ponce (DIENS, ENS-PSL)
  • Rufin VanRullen (CerCo, CNRS)

Call for contributions

We welcome contributions from early-career researchers, including Bachelor/Master/Ph.D. students, postdocs, or recently promoted assistant professors. The titles and short abstracts (1/2 pages max) should be written in English and sent to gautier.claisse@uca.fr and arthur.aubret@uca.fr by September 8th.


The contribution can present recently published research, on-going research, or a research project. We will give confirmation of oral/poster presentation for each contribution by September 15th. We aim to provide a friendly atmosphere for students to practice presenting their research in english. Registration is free but mandatory

Organizers

  • Arthur Aubret (Institut Pascal)
  • Gautier Claisse (Institut Pascal/Lapso)
  • Mehdi Gharbage (Institut Pascal/Michelin)
  • Céline Teulière (Institut Pascal)

Programme

Tentative program:


[9:00-9:15] Welcoming coffee

[9:15-9:30] Introduction sur l'apprentissage autosupervisé

[9:30-10:15] Dr. Oriane Siméoni

[10:15-10:30] Coffee break

[10:30-11:15] Prof. Diane Larlus: From Many Models to One: Multi-Teacher Distillation and Model Merging for Universal Visual Representations

[11:15-12:15] Poster session

[12:15-13:15] Lunch (buffet)

[13:15-14:00] Prof. Jean Ponce: Dual Perspectives on Non-Contrastive Self-Supervised Learning

[14:00-14:45] Oral contributions 1

[14:45-15:00] Coffee break

[15:00-15:45] Prof. Rufin VanRullen

[15:45-16:30] Oral contributions 2

[16:30] Discussion




Les commentaires sont clos.