🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A generative world for general-purpose robotics & embodied AI learning.

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

End-to-End Object Detection with Transformers

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

An educational resource to help anyone learn deep reinforcement learning.

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Vector (and Scalar) Quantization, in Pytorch

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

Collection of reinforcement learning algorithms

[ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.

Web-based 3D visualization + Python

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

A large-scale benchmark and learning environment.

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

RLinf is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning.