Machine Learning

Applying machine learning science to Facebook products

Connecting people with the content and stories they care about most.

Machine learning and Applied Machine Learning is essential to Facebook. It helps people discover new content and connect with the stories they care the most about. Our machine learning and applied machine learning researchers and engineers develop machine learning algorithms that rank feeds, ads and search results, and create new text understanding algorithms that keep spam and misleading content at bay. New computer vision algorithms can “read” images and videos to the blind and display over 2 billion translated stories every day, speech recognition systems automatically caption the videos that play in your news feed, and we create new magical visual experiences such as turning panorama photos into fully interactive 360 photos.

“We seek to advance the state of the art in machine learning for maximum impact, and our efforts form the glue between science and research and Facebook experiences.” Joaquin Quinonero Candela, Director of Applied Machine Learning

Latest Publications

All Publications

Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills

Eric Michael Smith, Mary Williamson, Kurt Shuster, Jason Weston, Y-Lan Boureau

ACL - June 19, 2020

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

Shunsuke Saito, Tomas Simon, Jason Saragih, Hanbyul Joo

CVPR - June 16, 2020

ARCH: Animatable Reconstruction of Clothed Humans

Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung

CVPR - June 15, 2020

You2Me: Inferring Body Pose in Egocentric Video via First and Second Person Interactions

Evonne Ng, Donglai Xiang, Hanbyul Joo, Kristen Grauman

CVPR - June 14, 2020

Downloads & Projects

View all Downloads & Projects

The bAbI Project is organized towards the goal of automatic text understanding and reasoning.

Stack RNN is a project gathering the code from the paper Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets by Armand Joulin and Tomas Mikolov.

Torch is a scientific computing framework with wide support for machine learning algorithms. It is easy to use and efficient, thanks to an easy and fast scripting language, LuaJIT, and an underlying C/CUDA implementation.

Careers at Facebook Research
Want to solve some of the most challenging technology problems?