Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

This is toolbox to generate world-models from gym environments.

Download files from osf.io

Reliable, minimal and scalable library for pretraining foundation and world models

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Reference PyTorch implementation and models for DINOv3

PyTorch code and models for VJEPA2 self-supervised learning from video.

Label-Efficient LiDAR Panoptic Segmentation

Tensors and Dynamic neural networks in Python with strong GPU acceleration

A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning

Linear Probing and clustering segmentation based on iBOT's pretrained model