Explore the latest in Facebook Research through publications

All Publications

January 1, 2021 Mahmoud Assran, Michael Rabbat
Paper

Asynchronous Gradient-Push

We consider a multi-agent framework for distributed optimization where each agent has access to a local smooth strongly convex function, and the collective goal is to achieve consensus on the parameters that minimize the sum of the agents’ local functions. We propose an algorithm wherein each agent operates asynchronously and independently of the other agents.
Paper
August 17, 2020 Lei Xiao, Salah Nouri, Matt Chapman, Alexander Fix, Douglas Lanman, Anton Kaplanyan
Paper

Neural Supersampling for Real-time Rendering

Following the recent advances in image and video superresolution in computer vision, we propose a machine learning approach that is specifically tailored for high-quality upsampling of rendered content in real-time applications.
Paper
July 19, 2020 Jungdam Won, Deepak Gopinath, Jessica Hodgins
Paper

A Scalable Approach to Control Diverse Behaviors for Physically Simulated Characters

Human characters with a broad range of natural looking and physically realistic behaviors will enable the construction of compelling interactive experiences. In this paper, we develop a technique for learning controllers for a large set of heterogeneous behaviors.
Paper
July 8, 2020 Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov, Luke Zettlemoyer
Paper

BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.
Paper
July 6, 2020 Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams, Ryan Cotterell
Paper

Information-Theoretic Probing for Linguistic Structure

We propose an information-theoretic operationalization of probing as estimating mutual information that contradicts this received wisdom: one should always select the highest performing probe one can, even if it is more complex, since it will result in a tighter estimate, and thus reveal more of the linguistic information inherent in the representation.
Paper
July 6, 2020 Shuo Sun, Francisco (Paco) Guzman, Lucia Specia
Paper

Are we Estimating or Guesstimating Translation Quality?

Recent advances in pre-trained multilingual language models lead to state-of-the-art results on the task of quality estimation (QE) for machine translation. A carefully engineered ensemble of such models dominated the QE shared task at WMT 2019. Our in-depth analysis, however, shows that the success of using pre-trained language models for QE is overestimated due to three issues we observed in current QE datasets.
Paper
July 5, 2020 Pengcheng Yin, Graham Neubig, Wen-tau Yih, Sebastian Riedel
Paper

TABERT: Pretraining for Joint Understanding of Textual and Tabular Data

In this paper we present TABERT, a pretrained LM that jointly learns representations for NL sentences and (semi-)structured tables.
Paper
July 3, 2020 Gabriel Schwartz, Shih-En Wei, Te-Li Wang, Stephen Lombardi, Tomas Simon, Jason Saragih, Yaser Sheikh
Paper

The Eyes Have It: An Integrated Eye and Face Model for Photorealistic Facial Animation

Although methods have been proposed to redirect gaze in 2D teleconferencing situations to enable eye contact, 2D video conferencing lacks the 3D immersion of real life. To address these problems, we develop a system for face-to-face interaction in VR that focuses on reproducing photorealistic gaze and eye contact.
Paper
July 3, 2020 Andrew Maimone, Junren Wang
Paper

Holographic Optics for Thin and Lightweight Virtual Reality

We present a class of display designs combining holographic optics, directional backlighting, laser illumination, and polarization-based optical folding to achieve thin, lightweight, and high performance near-eye displays for virtual reality.
Paper
June 29, 2020 Fred Lin, Antonio Davoli, Imran Akbar, Sukumar Kalmanje, Leandro Silva, John Stamford, Yanai Golany, Jim Piazza, Sriram Sankar
Paper

Predicting Remediations for Hardware Failures in Large-Scale Datacenters

In this paper, we present a machine learning framework that predicts the required remediations for undiagnosed failures, based on the similar repair tickets closed in the past.
Paper