Website

Nvlabs

Publisher of Pacnet, MUNIT and OmniVinci

  • 64 active products

Consolidated Product Portfolio

  • ASPIRE

    ASPIRE: Agentic /Skills Discovery for Robotics

    Skills AssessmentOpen Source
  • AlpaSim

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

    Machine Learning Model TrainingOpen Source
  • Alpamayo

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

    Machine Learning Model TrainingOpen Source
  • Alpamayo Coc Autolabeler

    NVIDIA CoC Autolabeler is an open autolabeling pipeline for autonomous vehicles that generates Chain-of-Causation reasoning labels and meta-actions from raw driving clips.

    Annotation LabelingOpen Source
  • AutoGaze

    AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.

    Video EditingOpen Source
  • COAT

    [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training

    Machine Learning Model TrainingOpen Source
  • Catk

    Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models. CVPR Oral 2025.

    Fine Tuning PlatformOpen Source
  • CenterPose

    Single-Stage Keypoint-based Category-level Object Pose Estimation from an RGB Image (ICRA 2022)

    Machine Learning Model TrainingOpen Source
  • Condensa

    Programmable Neural Network Compression

    Machine Learning Model TrainingOpen Source
  • DREAM

    DREAM: Deep Robot-to-Camera Extrinsics for Articulated Manipulators (ICRA 2020)

    Machine Learning Model TrainingOpen Source
  • Dex Ycb Toolkit

    A Python package that provides evaluation and visualization tools for the DexYCB dataset

    Chart VisualizationOpen Source
  • DiffiT

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

    Ai Image EditingOpen Source
  • DoRA

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

    Machine Learning Model TrainingOpen Source
  • EDM

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

    Generative Engine OptimizationOpen Source
  • ENPIRE

    ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop physical trial, error, and evolution

    Ai Coding AgentOpen Source
  • EdgeRunner

    [ICLR 2025] EdgeRunner: Auto-regressive Auto-encoder for Efficient Mesh Generation

    Ai Art GenerationOpen Source
  • FAN

    Official PyTorch implementation of Fully Attentional Networks

    Machine Learning Model TrainingOpen Source
  • FB-BEV

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

    Machine Learning Model TrainingOpen Source
  • Fast-dLLM

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

    Llm OrchestrationOpen Source
  • FastGen

    NVIDIA FastGen: Fast Generation from Diffusion Models

    Ai Art GenerationOpen Source
  • FasterViT

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

    Machine Learning Model TrainingOpen Source
  • FreeSOLO

    FreeSOLO for unsupervised instance segmentation, CVPR 2022

    Machine Learning Model TrainingOpen Source
  • GCVit

    [ICML 2023] Official PyTorch implementation of Global Context Vision Transformers

    Machine Learning Model TrainingOpen Source
  • GDPO

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

    Llm OrchestrationOpen Source
  • GR00T-WholeBodyControl

    GR00T-WholeBodyControl Documentation — GR00T-WholeBodyControl Documentation

    Iot PlatformOpen Source
  • GRAIL

    A digital data-generation pipeline that synthesizes humanoid loco-manipulation data from 3D assets and video priors.

    Synthetic Data GenerationOpen Source
  • Instant Ngp

    Instant neural graphics primitives: lightning fast NeRF and more

    Machine Learning Model TrainingOpen Source
  • Intrinsic3D

    Intrinsic3D - High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting (ICCV 2017)

    Machine Learning Model TrainingOpen Source
  • Long Video GAN

    Official PyTorch implementation of LongVideoGAN

    Ai Video CreationOpen Source
  • Long-RL

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

    Llm OrchestrationOpen Source
  • LongLive

    Long Video Gen Infrastructure

    Ai Video CreationOpen Source
  • LongSplat

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

    Machine Learning Model TrainingOpen Source
  • MUNIT

    Multimodal Unsupervised Image-to-Image Translation

    Machine Learning Model TrainingOpen Source
  • MambaVision

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

    Machine Learning Model TrainingOpen Source
  • MaskLLM

    [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models

    Llm OrchestrationOpen Source
  • MatchLib

    SystemC/C++ library of commonly-used hardware functions and components for HLS.

    Hardware Lifecycle ManagementOpen Source
  • MobilityGen

    Data Generation Pipeline for Mobility

    Synthetic Data GenerationOpen Source
  • Neural Rx

    Real-Time Inference of 5G NR Multi-user MIMO Neural Receivers

    Machine Learning Model TrainingOpen Source
  • Neuralangelo

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

    Machine Learning Model TrainingOpen Source
  • Nvdiffmodeling

    Differentiable rasterization applied to 3D model simplification tasks

    3d ModelingOpen Source
  • Nvdiffrec

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

    Machine Learning Model TrainingOpen Source
  • ODISE

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

    Machine Learning Model TrainingOpen Source
  • OmniVinci

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

    Machine Learning Model TrainingOpen Source
  • PS3

    Scaling Vision Pre-Training to 4K Resolution

    Machine Learning Model TrainingOpen Source
  • PWC-Net

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

    Machine Learning Model TrainingOpen Source
  • Pacnet

    Pixel-Adaptive Convolutional Neural Networks (CVPR '19)

    Machine Learning Model TrainingOpen Source
  • PartPacker

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

    Ai Art GenerationOpen Source
  • PointWorld

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

    Robotic Process AutomationOpen Source
  • QUEEN

    Official PyTorch implementation of QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos (NeurIPS 2024)

    Machine Learning Model TrainingOpen Source
  • QeRL

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

    Llm OrchestrationOpen Source
  • SANA

    SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

    Machine Learning Model TrainingOpen Source
  • SPADE

    Semantic Image Synthesis with SPADE

    Ai Image EditingOpen Source
  • Selfsupervised Denoising

    High-Quality Self-Supervised Deep Image Denoising - Official TensorFlow implementation of the NeurIPS 2019 paper

    Ai Image EditingOpen Source
  • Sionna

    Sionna - A hardware-accelerated differentiable open-source library for research on communication systems

    Machine Learning Model TrainingOpen Source
  • Sionna Rk

    Sionna Research Kit: A GPU-Accelerated Research Platform for AI-RAN

    Digital TwinOpen Source
  • Solar

    Speed of Light Analysis for ML Model Runtime

    Model DeploymentOpen Source
  • Taylor_pruning

    Pruning Neural Networks with Taylor criterion in Pytorch

    Machine Learning Model TrainingOpen Source
  • Timeloop

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

    Data ModelingOpen Source
  • Tiny Cuda Nn

    Lightning fast C++/CUDA neural network framework

    Machine Learning Model TrainingOpen Source
  • ToolOrchestra

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

    Machine Learning Model TrainingOpen Source
  • Verilog Eval

    Verilog evaluation benchmark for large language model

    Llm OrchestrationOpen Source
  • VoxFormer

    Official PyTorch implementation of VoxFormer [CVPR 2023 Highlight]

    Machine Learning Model TrainingOpen Source
  • Wetectron

    Weakly-supervised object detection.

    Machine Learning Model TrainingOpen Source
  • rCM

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

    Ai Video CreationOpen Source

Company Profile & Strategy

Nvlabs veröffentlicht 47 Produkte auf nvlabs.github.io, einschließlich Pacnet, MUNIT und OmniVinci. Pacnet: Pixel-adaptive Convolutional Neural Networks (CVPR '19).

Open-Source Footprint

64 repositories88.5K stars

Save & manage the vendor's products in Productapp.

Save and manage this vendor's products in Productapp.

Start free trial