We’ve built data2vec, the first general high-performance self-supervised algorithm for speech, vision, and text. When applied to different modalities, it matches or outperforms the best self-supervised algorithms.

January 20, 2022

Help Us Pioneer the Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.

Join Our Team

Tools

Tools Frameworks & Tools

Datasets

Research

Research Research Areas Notable Papers Recent Publications Fundamental & Applied Recent Projects

Blog

Blog Read Blog

People

People People Profiles

Join Us

Join Us Jobs AI Residency Program RAISE Program

Events

Terms

Tools for Advancing the World's AI

Cutting edge open source frameworks, tools, libraries, and models for research exploration to large-scale production deployment.

Frameworks & Tools

PyTorch

PyTorch is an open source deep learning framework built to be flexible and modular for research, with the stability and support needed for production deployment. It enables fast, flexible experimentation through a tape-based autograd system designed for immediate and python-like execution.

ONNX

Tensor Comprehensions

Glow

FAISS

StarSpace

Visdom

DynaBench

COVID-19 Forecasting

Ego4D

Libraries & Models

Computer Vision

Detectron2

DensePose

WSL Embeddings

Language

PyText

FastText

Translate

ParlAI

Fairseq

MUSE

VizSeq

CoVoST

KILT Benchmarking

Speech

Wav2letter

Libri-light

Reasoning

ELF

ELF OpenGo

House3D

PHYRE

TorchCraft

ReAgent

Multimodal

Hateful Memes

Recent Work

RESEARCH

Introducing the AI Research SuperCluster — Meta’s cutting-edge AI supercomputer for AI research

NLP

The first high-performance self-supervised algorithm that works for speech, vision, and text

Help Us Pioneer the Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.