NVlabs

Instant neural graphics primitives: lightning fast NeRF and more

StyleGAN - Official TensorFlow Implementation

StyleGAN2 - Official TensorFlow Implementation

SANA & Sol: Efficient Generative Models and Full-Stack Training & Inference Engines for Image, Video, and World Modeling

Semantic Image Synthesis with SPADE

Official PyTorch implementation of StyleGAN3

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

Lightning fast C++/CUDA neural network framework

StyleGAN2-ADA - Official PyTorch implementation

Flickr-Faces-HQ Dataset (FFHQ)

NVIDIA's Deep Imagination Team's PyTorch Library

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t,...

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

Official PyTorch implementation of SegFormer

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

SoL-Pi: Scaling Auto-Research Loops for Efficient Agent Harnesses

[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

Long Video Gen / World Model / World Action Model (Embodied) Infrastructure

Multimodal Unsupervised Image-to-Image Translation

ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

[CVPR 2025] Official PyTorch Implementation of MambaVision: A Hybrid Mamba-Transformer Vision Backbone

NVIDIA Alpamayo 1 Nano is an open 10B reasoning VLA model for autonomous vehicles that pairs driving trajectories with Chain-of-Causation reasoning.

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

Official repository for "AM-RADIO: Reduce All Domains Into One"

CUDA Accelerated Robot Library

Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation

Pytorch implementation for few-shot photorealistic video-to-video translation.

PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)

InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds

Sionna: An Open-Source Library for Research on Communication Systems

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Translate images to unseen domains in the test time with few example images.

Noise2Noise: Learning Image Restoration without Clean Data - Official TensorFlow implementation of the ICML 2018 paper

Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.

[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning

[CVPR 2023] BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".

Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral)

AlpaSim is an open-source autonomous vehicle simulation platform designed for development and testing of end-to-end AV policies

Alias-Free GAN project website and code

Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

NVIDIA FastGen: Fast Generation from Diffusion Models

The Official PyTorch Implementation of "NVAE: A Deep Hierarchical Variational Autoencoder" (NeurIPS 2020 spotlight paper)

cuTile Rust provides a safe, tile-based kernel programming DSL for the Rust programming language. It features a safe host-side API for passing tensors to asynchronously executed kernel functions.

[CVPR 2026 Best Paper Finalist & NeurIPS 2026]

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

Official implementation of MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives (SIGGRAPH 2026)

ASPIRE: Agentic /Skills Discovery for Robotics

[CVPR 2025] Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering

Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

Cosmos Policy

SOMA: Unifying Parametric Human Body Models

EDM2 and Autoguidance -- Official PyTorch implementation

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

Efficient Part-level 3D Object Generation via Dual Volume Packing

[ICCV 2025] LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception

Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.

ToolOrchestra is an end-to-end RL training framework for orchestrating tools and agentic workflows.

HOVER

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Initial public release of code, data, and model weights for FourCastNet

[ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

This code corresponds to simulation environments used as part of the MimicGen project.

A tool for visualizing and communicating the errors in rendered images.

Hybrid CPU/GPU implementation of the A3C algorithm for deep reinforcement learning.

Our first fully AI generated deep learning system

PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

Official repo for GraspGen: A Diffusion-based Framework for 6-DOF Grasping

A simulation benchmarking platform for evaluating generalist robot policies

PlaneRCNN detects and reconstructs piece-wise planar surfaces from a single RGB image

🤖 GRAIL is a fully digital data-generation pipeline that synthesizes humanoid loco-manipulation data from world models. 🌟 CoRL 2026 (Best Paper Award Finalist)

Monocular whole-body 3D human pose estimation using the SOMA body model

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

Efficient 6-DoF Grasp Generation in Cluttered Scenes

Timeloop performs modeling, mapping and code-generation for tensor algebra workloads on various accelerator architectures.

[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

Official PyTorch implementation of Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion (CVPR 2020)

[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation

Pixel-Adaptive Convolutional Neural Networks (CVPR '19)

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Differentiable rasterization applied to 3D model simplification tasks

VLA-0: Building State-of-the-Art VLAs with Zero Modification