Bringing the world closer together by advancing artificial intelligence

At Facebook AI, we're connecting people to what they care about, powering new, meaningful experiences, and advancing the state-of-the-art through open research and accessible tooling.

See Our Research

RESEARCH

Research Areas

Our teams accelerate research breakthroughs across both existing and new learning paradigms to develop state-of-the-art AI that has a positive impact on people and society.

Computer Vision

Understanding the visual world around us

Conversational AI

Creating personalized and meaningful interactions

Integrity

Building AI solutions to keep people safe on social platforms

Natural Language Processing

Next generation text understanding and generation

Ranking & Recommendations

Connecting people to what's most meaningful

Systems Research

Developing novel algorithmic, software, and hardware techniques

Theory

Laying foundations for artificial intelligence

Speech & Audio

Powering voice interfaces and audio content understanding

Human & Machine Intelligence

Building algorithms inspired by, and compatible with, human cognition

Additional Areas

Reinforcement learning, robotics, graphics, and more coming soon

Recent Publications

Computer Vision

Cycle-Consistency for Robust Visual Question Answering

We introduce a new evaluation protocol and associated dataset (VQA-Rephrasings) and show that state-of-the-art VQA models are notoriously brittle to linguistic variations in questions.

Conversational AI

Engaging Image Chat: Modeling Personality in Grounded Dialogue

To achieve the long-term goal of machines being able to engage humans in conversation, our models should be engaging.

Integrity

Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

This paper studies an approach that aims to make image-recognition systems robust against adversarial images by performing nearest-neighbor searches for similar images in a web-scale database of billions of unlabeled images.

View All Publications

TOOLS

Open source tools, libraries, and models for cutting edge research to production deployment.

End-to-End

Accelerate development with tools that enable the workflow from research prototyping to deployment.

State of the Art

Tap into the latest breakthroughs developed by Facebook AI and deployed in products used by billions.

Open & Modular

Work with a broad ecosystem of open source tools and libraries designed to be modular and interoperable.

Open-Source AI 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

ONNX is an open format for deep learning models, allowing AI developers to easily move between state-of-the-art tools.

Glow

Glow is a machine learning compiler that accelerates the performance of deep learning frameworks on different hardware platforms.

Join Us

Tackle the world's most complex technology challenges.

Join Our Team

Latest News

Visit the AI Blog for updates on recent publications, new tools, and more.

Visit Blog