Research Areas

Giving people the power to share and connect requires constant innovation

At Facebook, research permeates everything we do. We believe the most interesting research questions are derived from real world problems. Working on cutting edge research with a practical focus, we push product boundaries every day. At the same time, we publish papers, give talks, and collaborate broadly with the academic community.

We solve real-world problems that impact billions of people in areas such as:

Latest Publications

All Publications

SIGGRAPH ASIA - December 14, 2021

Modeling Clothing as a Separate Layer for an Animatable Human Avatar

Donglai Xiang, Fabián Prada, Timur Bagautdinov, Weipeng Xu, Yuan Dong, He Wen, Jessica Hodgins, Chenglei Wu

ASRU - December 13, 2021

Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems

Yangyang Xia, Buye Xu, Anurag Kumar

IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) - December 13, 2021

Kaizen: Continuously Improving Teacher Using Exponential Moving Average For Semi-supervised Speech Recognition

Vimal Manohar, Tatiana Likhomanenko, Qiantong Xu, Wei-Ning Hsu, Ronan Collobert, Yatharth Saraf, Geoffrey Zweig, Abdelrahman Mohamed

ISAAC - December 5, 2021

On the Extended TSP Problem

Julián Mestre, Sergey Pupyrev, Seeun William Umboh

3DV - November 18, 2021

Recovering Real-World Reflectance Properties and Shading From HDR Imagery

Bjoern Haefner, Simon Green, Alan Oursland, Daniel Andersen, Michael Goesele, Daniel Cremers, Richard Newcombe, Thomas Whelan

EMNLP - November 10, 2021

Cross-Policy Compliance Detection via Question Answering

Marzieh Saeidi, Majid Yazdani, Andreas Vlachos

CoNLL - November 9, 2021

Generalising to German Plural Noun Classes, from the Perspective of a Recurrent Neural Network

Verna Dankers, Anna Langedijk, Kate McCurdy, Adina Williams, Dieuwke Hupkes

EMNLP - November 7, 2021

Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications

Shuo Sun, Ahmed El-Kishky, Vishrav Chaudhary, James Cross, Francisco Guzmán, Lucia Specia

Downloads & Projects

View all Downloads & Projects

PyTorch is a Python package that provides two high-level features: tensor computation (like NumPy) with strong GPU acceleration and deep neural networks built on a tape-based autograd system.

Dense human pose estimation aims at mapping all human pixels of an RGB image to the 3D surface of the human body.

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?