Matt Le
RESEARCH ENGINEER | NEW YORK CITY, UNITED STATES
Matt is a Research Engineer at Facebook AI Research (FAIR) in NYC. Before joining FAIR, he spent 2 years working at the Mount Sinai School of Medicine in the Department of Global Health. Prior to that, he received his M.S. in Computer Science from the Rochester Institute of Technology and a B.S. in Computer Science from the University of Minnesota - Twin Cities. At FAIR, Matt has worked on representation learning, machine translations, and time series forecasting.
Matt's Work
Matt's Publications
December 16, 2025
SPEECH & AUDIO
COMPUTER VISION
SAM Audio: Segment Anything in Audio
Yi-Chiao Wu, Julius Richter, Andros Tjandra, Ann Lee, Apoorv Vyas, Bowen Shi, Christoph Feichtenhofer, Helin Wang, John Hoffman, Luya Gao, Matt Le, Piotr Dollar, Sanyuan Chen, Wei-Ning Hsu
December 16, 2025
December 16, 2025
SPEECH & AUDIO
COMPUTER VISION
Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
Heng-Jui Chang, Cheng-Fu Yang, Julius Richter, Ann Lee, Apoorv Vyas, Bernie Huang, Christoph Feichtenhofer, Luya Gao, Matt Le, Piotr Dollar, Sanyuan Chen, Wei-Ning Hsu
December 16, 2025
February 07, 2025
RESEARCH
SPEECH & AUDIO
Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound
Andros Tjandra, Ann Lee, Apoorv Vyas, Baishan Guo, Bowen Shi, Brian Ellis, Carleigh Wood, John Hoffman, Matt Le, Nick Zacharov, Sanyuan Chen, Wei-Ning Hsu, Yi-Chiao Wu
February 07, 2025
December 10, 2024
CORE MACHINE LEARNING
Flow Matching Guide and Code
Peter Holderrieth, Neta Shaul, Heli Ben Hamu, Yaron Lipman, Brian Karrer, David Lopez-Paz, Itai Gat, Marton Havasi, Matt Le, Ricky Chen
December 10, 2024
June 17, 2024
COMPUTER VISION
CORE MACHINE LEARNING
Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
Neta Shaul, Yaron Lipman, Albert Pumarola, Ali Thabet, Matt Le, Ricky Chen, Uriel Singer
June 17, 2024
March 05, 2024
SPEECH & AUDIO
Generative Pre-training for Speech with Flow Matching
Wei-Ning Hsu, Alex Liu, Andros Tjandra, Apoorv Vyas, Bowen Shi, Matt Le
March 05, 2024
December 11, 2023
SPEECH & AUDIO
Audiobox: Unified Audio Generation with Natural Language Prompts
Wei-Ning Hsu, Akinniyi Akinyemi, Alice Rakotoarison, Andros Tjandra, Apoorv Vyas, Baishan Guo, Bapi Akula, Bowen Shi, Brian Ellis, Ivan Cruz, Jeff Wang, Jiemin Zhang, Mary Williamson, Matt Le, Rashel Moritz, Robbie Adkins, William Ngan, Xinyue Zhang, Yael Yungster, Yi-Chiao Wu
December 11, 2023
June 16, 2023
SPEECH & AUDIO
NLP
Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
Matt Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Jay Mahadeokar, Leda Sari, Mary Williamson, Rashel Moritz, Vimal Manohar, Wei-Ning Hsu, Yossef (Yossi) Adi
June 16, 2023
September 23, 2020
ML APPLICATIONS
Neural Relational Autoregression for High-Resolution COVID-19 Forecasting
Maximilian Nickel, Levent Sagun, Mark Ibrahim, Matt Le, Timothee Lacroix
September 23, 2020
October 25, 2019
RESEARCH
NLP
Revisiting the Evaluation of Theory of Mind through Question Answering
Max Nickel, Matt Le, Y-Lan Boureau
October 25, 2019
Our approach
Latest news
Foundational models
Meta © 2026