Picture for Vincent-Pierre Berges

Vincent-Pierre Berges

Learning to Reason for Factuality

Add code
Aug 07, 2025
Viaarxiv icon

Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D

Add code
Apr 19, 2025
Viaarxiv icon

LIFT-GS: Cross-Scene Render-Supervised Distillation for 3D Language Grounding

Add code
Feb 27, 2025
Viaarxiv icon

Memory Layers at Scale

Add code
Dec 12, 2024
Figure 1 for Memory Layers at Scale
Figure 2 for Memory Layers at Scale
Figure 3 for Memory Layers at Scale
Figure 4 for Memory Layers at Scale
Viaarxiv icon

Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots

Add code
Oct 19, 2023
Figure 1 for Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
Figure 2 for Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
Figure 3 for Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
Figure 4 for Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
Viaarxiv icon

What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?

Add code
Oct 03, 2023
Figure 1 for What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?
Figure 2 for What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?
Figure 3 for What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?
Figure 4 for What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?
Viaarxiv icon

Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second

Add code
Jun 13, 2023
Figure 1 for Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
Figure 2 for Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
Figure 3 for Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
Figure 4 for Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
Viaarxiv icon

Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?

Add code
Mar 31, 2023
Figure 1 for Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Figure 2 for Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Figure 3 for Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Figure 4 for Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Viaarxiv icon

Offline Visual Representation Learning for Embodied Navigation

Add code
Apr 27, 2022
Figure 1 for Offline Visual Representation Learning for Embodied Navigation
Figure 2 for Offline Visual Representation Learning for Embodied Navigation
Figure 3 for Offline Visual Representation Learning for Embodied Navigation
Figure 4 for Offline Visual Representation Learning for Embodied Navigation
Viaarxiv icon

On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning

Add code
Nov 10, 2021
Figure 1 for On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning
Figure 2 for On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning
Figure 3 for On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning
Figure 4 for On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning
Viaarxiv icon