[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Unified framework for robot learning built on NVIDIA Isaac Sim

Agent Learning Framework https://alf.readthedocs.io

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

Robust Speech Recognition via Large-Scale Weak Supervision

Heterogeneous Pre-trained Transformer (HPT) is a scalable policy learner for robotics.

unitree Go2 robot learns locomotion with N-P3O algorithm and HIM alike policy trained by isaacgym

openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for 250+ supported car makes and models.

Inference code for Llama models

Grok open release

An open autonomous driving platform

Repository of paper https://arxiv.org/abs/1612.01105

Semi-direct Visual Odometry

An OpenCV based implementation of Monocular Visual Odometry

Fast R-CNN

Caffe fork that supports Fast R-CNN

Deep Learning GPU Training System

R-CNN: Regions with Convolutional Neural Network Features

Caffe

Point Cloud Library (PCL)