facebookresearch

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.

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.

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

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

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

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.

Reference PyTorch implementation and models for DINOv3

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

Implementation of Nougat Neural Optical Understanding for Academic Documents

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

ImageBind One Embedding Space to Bind Them All

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

SAM 3D Objects

Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristics, detecting change points and anomalies, to forecasting future trends.

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

High-resolution models for human tasks.

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

A data augmentations library for audio, image, text, and video.

CoTracker is a model for tracking any point (pixel) on a video.

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

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.

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

[CVPR 2026 Oral] VGGT Omega

A Python toolbox for performing gradient-free optimization

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

An implementation of a deep learning recommendation model (DLRM)

State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

A flexible, high-performance 3D simulator for Embodied AI research.

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

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.

A deep learning library for video understanding research.

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.

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

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

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

Large Concept Models: Language modeling in a sentence representation space

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

Schedule-Free Optimization in PyTorch

Collection of common code that's shared among different research projects in FAIR computer vision team.

FAIR Chemistry's library of machine learning methods for chemistry

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

Code for BLT research paper

A library for differentiable nonlinear optimization

Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".

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

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

Training Large Language Model to Reason in a Continuous Latent Space

MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

VGGSfM: Visual Geometry Grounded Deep Structure From Motion

Uncommon Objects in 3D dataset

The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

Mobile manipulation research tools for roboticists

Tooling for the Common Objects In 3D dataset.

Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight

code for Mesh R-CNN, ICCV 2019

FAIR Sequence Modeling Toolkit 2

Hiera: A fast, powerful, and simple hierarchical vision transformer.

Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".

A modular embodied agent architecture and platform for building embodied agents

1K resolution vision transformers pretrained on 1B human images.

Mobile vision models and code

Non-invasive decoding of typed sentences from MEG and EEG brain recordings using a convolutional encoder, transformer, and character-level language model.

Can Language Models Rebuild Programs From Scratch?

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

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

Code for the ShapeR research paper

projectaria_tools is an C++/Python open-source toolkit to interact with Project Aria data.

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.

MADGRAD Optimization Method

Ocean is the in-house framework for Computer Vision (CV) and Augmented Reality (AR) applications at Meta. It is platform independent and is mainly implemented in C/C++.

[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations

The first behavioral foundation model to control a virtual physics-based humanoid agent for a wide range of whole-body tasks.

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

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

The balance python package offers a simple workflow and methods for dealing with biased data samples when looking to infer from them to some target population of interest.

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.

Open and efficient video and image watermarking

Unified automatic quality assessment for speech, music, and sound.

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

[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"

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

SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.

Official code for the CVPR 2025 paper "Navigation World Models".

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

Pippo: High-Resolution Multi-View Humans from a Single Image

Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

MLGym A New Framework and Benchmark for Advancing AI Research Agents

Code for the Boxer research paper

Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https://mv-dust3rp.github.io/

For optimization algorithm research and development.

Source Code for Paper "OrienterNet Visual Localization in 2D Public Maps with Neural Matching"

Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)

A library to analyze PyTorch traces.

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.

A general physic-based retargeting framework.

D-Adaptation for SGD, Adam and AdaGrad

Official implementation of the paper "The Stable Signature Rooting Watermarks in Latent Diffusion Models"

Dr. Zero Self-Evolving Search Agents without Training Data

An Open-source Streaming High-fidelity Neural Audio Codec

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.

The repository for the largest and most comprehensive empirical study of visual foundation models for Embodied AI (EAI).