PyTorch code and models for VJEPA2 self-supervised learning from video.
Repository Index
132,241 visible repositories in the index
1–9 of 9 · Most stars
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure strategies, a volumetric reconstruction module, integrated depth-prediction models, and semantic segmentation capabilities for enhanced scene understanding.
- 3d-reconstruction
- depth-prediction
- feature-matching
- global-features
Long Video Gen / World Model / World Action Model (Embodied) Infrastructure
- real-time
- infra
- long
- nvfp4
[RSS 2026] Causal video-action world model for generalist robot control
Official code of Motus: A Unified Latent Action World Model
- robotics
- world-model
- video-generation
- unidiffuser
This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym
- deep-reinforcement-learning
- dexterous-robotic-hand
- reinforcement-learning
Nvidia Isaac Video to Data Pipeline
First release for Can LLMs Debug Robots by Editing Their Weights? Code, 65-row edit, 16 experiment logs and evidence. V2 and real-robot experiments in progress.
- model-editing
- robotics
- vision-language-action
- weight-space-programming
Video-action policy for robot arms