Picture for Quentin Garrido

Quentin Garrido

FAIR, LIGM

Intuitive physics understanding emerges from self-supervised pretraining on natural videos

Add code
Feb 17, 2025
Viaarxiv icon

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

Add code
Aug 09, 2024
Figure 1 for UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
Figure 2 for UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
Figure 3 for UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
Figure 4 for UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
Viaarxiv icon

An Introduction to Vision-Language Modeling

Add code
May 27, 2024
Figure 1 for An Introduction to Vision-Language Modeling
Figure 2 for An Introduction to Vision-Language Modeling
Figure 3 for An Introduction to Vision-Language Modeling
Viaarxiv icon

Learning and Leveraging World Models in Visual Representation Learning

Add code
Mar 01, 2024
Figure 1 for Learning and Leveraging World Models in Visual Representation Learning
Figure 2 for Learning and Leveraging World Models in Visual Representation Learning
Figure 3 for Learning and Leveraging World Models in Visual Representation Learning
Figure 4 for Learning and Leveraging World Models in Visual Representation Learning
Viaarxiv icon

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

Add code
Jul 11, 2023
Viaarxiv icon

A Cookbook of Self-Supervised Learning

Add code
Apr 24, 2023
Figure 1 for A Cookbook of Self-Supervised Learning
Figure 2 for A Cookbook of Self-Supervised Learning
Figure 3 for A Cookbook of Self-Supervised Learning
Figure 4 for A Cookbook of Self-Supervised Learning
Viaarxiv icon

Self-supervised learning of Split Invariant Equivariant representations

Add code
Feb 14, 2023
Figure 1 for Self-supervised learning of Split Invariant Equivariant representations
Figure 2 for Self-supervised learning of Split Invariant Equivariant representations
Figure 3 for Self-supervised learning of Split Invariant Equivariant representations
Figure 4 for Self-supervised learning of Split Invariant Equivariant representations
Viaarxiv icon

The Robustness Limits of SoTA Vision Models to Natural Variation

Add code
Oct 24, 2022
Viaarxiv icon

RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank

Add code
Oct 05, 2022
Figure 1 for RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank
Figure 2 for RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank
Figure 3 for RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank
Figure 4 for RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank
Viaarxiv icon

Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head

Add code
Jun 27, 2022
Figure 1 for Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head
Figure 2 for Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head
Figure 3 for Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head
Figure 4 for Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head
Viaarxiv icon