Stars
Official code for the paper "Single-Line Drawing Vectorization"
Official Implementation of "Splat the Net: Radiance Fields with Splattable Neural Primitives"
Reference PyTorch implementation and models for DINOv3
PyTorch code and models for VJEPA2 self-supervised learning from video.
Open-source framework for the research and development of foundation models.
NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.
Record gamepad, keyboard, and mouse inputs with OBS
Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.
Cross-platform C++ library for injection and consumption of input
Pure re-encoding of an mp4-h264 video file with the web APIs as well as in-depth description of how it works.
Python helpers to limit the number of threads used in native libraries that handle their own internal threadpool (BLAS and OpenMP implementations)
A multi-platform C library to provide global keyboard and mouse hooks from userland.
Website for hosting the Open Foundation Models Cheat Sheet.
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
PyTorch code and models for V-JEPA self-supervised learning from video.
Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.
Code for the paper "UVDoc: Neural Grid-based Document Unwarping"
Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.
Implementation of "Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision"
LichtFeld Studio: Where reality and the digital world blend.