Meta Research 的公共 GitHub 足迹

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A library for efficient similarity search and clustering of dense vectors.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

End-to-End Object Detection with Transformers

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

PyTorch code and models for the DINOv2 self-supervised learning method.

Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

Foundational Models for State-of-the-Art Speech and Text Translation

Reference PyTorch implementation and models for DINOv3

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Hackable and optimized Transformers building blocks, supporting a composable construction.

Hydra is a framework for elegantly configuring complex applications

Code for the paper Hybrid Spectrogram and Waveform Source Separation

Implementation of Nougat Neural Optical Understanding for Academic Documents

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

ImageBind One Embedding Space to Bind Them All

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

SAM 3D Objects

Repo for external large-scale work

Code release for ConvNeXt model

A natural language modeling framework based on PyTorch

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Official DeiT repository

PyTorch code and models for VJEPA2 self-supervised learning from video.

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

Efficient 3D human pose estimation in video using 2D keypoint trajectories

PyTorch code and models for V-JEPA self-supervised learning from video.

A deep learning library for video understanding research.

The repository provides code for running inference with the Meta Segment Anything Audio Model (SAM-Audio), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.

[CVPR 2026 Oral] VGGT Omega

This repository contains the code to train and evaluate TRIBE v2, a multimodal model for brain response prediction

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

Self-referential self-improving agents that can optimize for any computable task

FAIR Chemistry's library of machine learning methods for chemistry

Code release for ConvNeXt V2 model

A library for differentiable nonlinear optimization

A Python framework for AI-driven character animation using neural networks.

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

A domain specific language to express machine learning workloads.

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

Learning Continuous Signed Distance Functions for Shape Representation

A large-scale dataset of both raw MRI measurements and clinical MRI images.

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Mobile manipulation research tools for roboticists

A method to increase the speed and lower the memory footprint of existing vision transformers.

Tooling for the Common Objects In 3D dataset.

Library for Knowledge Intensive Language Tasks

Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

Code for the ShapeR research paper

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

Can Language Models Rebuild Programs From Scratch?

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector

Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton with levels of detail;A body blendshape and pose corrective model; A facial blendshape model.Its design is friendly for both CG and CV communities.

Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

An open source library designed to provide community examples of Joint Embedding Predictive Architectures (JEPAs). It contains code and examples for learning representations from images, video, and action-conditioned video, as well as planning using JEPA-based models.

Efficient Universal Perception Encoder: a single on-device vision encoder with versatile representations that match or exceed specialized experts across multiple task domains.

LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

MLGym A New Framework and Benchmark for Advancing AI Research Agents

D-Adaptation for SGD, Adam and AdaGrad

Dr. Zero Self-Evolving Search Agents without Training Data

Scalable and Performant Data Loading

A library for human kinematic motion and numerical optimization solvers to apply human motion

Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".

This repository provides inference code to compute canopy height maps from aerial images, as described in the paper "Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar".

Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

Python suite for neuroscience research across all modalities.

DCPerf benchmark suite for hyperscale cloud applications

ATLAS Autoformalized Textbook Library At Scale

Code repository for emg2pose dataset and model benchmarks

Nymeria: a massive collection of multimodal egocentric daily motion in the wild

A pure-Python implementation of the Nvidia CuTe layout algebra intended to be approachable and easy to learn.

Library for converting clinical trial eligibility criteria to a machine-readable format.

Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"

MR.Q is a general-purpose model-free reinforcement learning algorithm.

MultiModal Audio Generation in Raw Waveform Space.

AIRA-dojo: a framework for developing and evaluating AI research agents

Differentiable Rendering Toolkit

Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.

A tutorial and a set of tools to compute depth-from-stereo with Project Aria Gen2 devices. This includes stereo image rectification as well as disparity estimation

Official code and data from DexWM ("World Models Can Leverage Human Videos for Dexterous Manipulation").

Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)

[CVPR 2026 Highlight] Leveraging latent world model's physics understanding to improve the physics plausibility of video generation

Code release for "Stochastic Optimal Control Matching"

Implementation of "Learning Fast 3D Gaussian Splatting Rendering using Continuous Level of Detail" presented at Eurographics 2025.

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models

LSRM is a SOTA, feed-forward 3D reconstruction model that generates high-fidelity, relightable 3D digital twins from sparse 2D views.

A companion repo for the BOUQuET dataset

The LuxRemix dataset is a synthetic dataset of 12K indoor scenes with per-light decomposition, which is designed for training models that decompose and re-mix indoor illumination from a single image.