Shang-Wen Daniel Li
RESEARCH SCIENTIST | MENLO PARK, UNITED STATES
Shang-Wen Li is a Research Scientist in Fundamental AI Research (FAIR) at Meta. His research focuses on large foundation models, vision and language multimodalities, and pretraining and self-supervised training. He leads foundation data research team at FAIR, which empowers many research and production use cases in pretraining across Meta from vision encoding, segmentation to MLLMs and video generation. He also worked at Amazon AWS, Amazon Alexa and Apple Siri as Research Scientist and earned his PhD from MIT CSAIL (Computer Science and Artificial Intelligence Laboratory).
Research Areas
Shang-Wen's Publications
April 17, 2025
HUMAN & MACHINE INTELLIGENCE
CONVERSATIONAL AI
Collaborative Reasoner: Self-improving Social Agents with Synthetic Conversations
Ansong Ni, Asli Celikyilmaz, Daniel Li (FAIR), Dong Wang, Gargi Ghosh, Ramya Raghavendra, Ruta Desai, Xinjie Lei, Yang Li
April 17, 2025
April 17, 2025
COMPUTER VISION
Perception Encoder: The best visual embeddings are not at the output of the network
Hanoona Rasheed, Junke Wang, Marco Monteiro, Andrea Madotto, Po-Yao Huang, Chen Wei, Christoph Feichtenhofer, Daniel Bolya, Daniel Li (FAIR), Hu Xu, Jathushan Rajasegaran, Jiale Zhi, Nikhila Ravi, Peize Sun, Piotr Dollar, Shiyu Dong, Tengyu Ma, Jang Hyun Cho
April 17, 2025
December 11, 2024
NLP
COMPUTER VISION
Meta CLIP 1.2
Saining Xie, Hu Xu, Bernie Huang, Ching-Feng Yeh, Christine Jou, Christoph Feichtenhofer, Daniel Li (FAIR), Ellen Tan, Gargi Ghosh, Jacob Kahn, Kim Hazelwood, Luke Zettlemoyer, Omer Levy, Philippe Brunet, Ramya Raghavendra, Scott Yih
December 11, 2024
April 22, 2024
NLP
Text Quality-Based Pruning for Efficient Training of Language Models
Vasu Sharma *, Armen Aghajanyan, Bernie Huang, Daniel Li (FAIR), Gargi Ghosh, Hu Xu, Karthik Padthe *, Kushal Tirumala, Luke Zettlemoyer, Newsha Ardalani, Russ Howes
April 22, 2024
August 22, 2023
SPEECH & AUDIO
NLP
SeamlessM4T—Massively Multilingual & Multimodal Machine Translation
Seamless Communication, Safiyyah Saleem, Abinesh Ramakrishnan, Alexandre Mourachko, Alice Rakotoarison, Amanda Kallet, Andy Chung, Ann Lee, Anna Sun, Bapi Akula, Benjamin Peloquin, Bernie Huang, Bokai Yu, Brian Ellis, Can Balioglu, Carleigh Wood, Changhan Wang, Christophe Ropers, Christopher Klaiber, Cynthia Gao, Daniel Li (FAIR), Daniel Licht, David Dale, Elahe Kalbassi, Ethan Ye, Gabriel Mejia Gonzalez, Guillaume Wenzek, Hady Elsahar, Hirofumi Inaguma, Holger Schwenk, Hongyu Gong, Igor Tufanov, Ilia Kulikov, Janice Lam, Jean Maillard, Jeff Wang (PM - AI), John Hoffman, Juan Pino, Justin Haaheim, Justine Kao, Prangthip Hasanti, Kaushik Ram Sadagopan, Kevin Heffernan, Kevin Tran, Loic Barrault, Maha Elbayad, Marta R. Costa-jussa, Mohamed Ramadan, Naji El Hachem, Ning Dong (AI), Onur Çelebi, Paco Guzmán, Paden Tomasello, Paul-Ambroise Duquenne, Peng-Jen Chen, Pengwei Li, Pierre Andrews, Ruslan Mavlyutov, Russ Howes, Skyler Wang, Somya Jain, Sravya Popuri, Tuan Tran, Vish Vogeti, Xutai Ma, Yilin Yang
August 22, 2023
July 14, 2023
NLP
COMPUTER VISION
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
Armen Aghajanyan, Adam Polyak, Arun Babu, Asli Celikyilmaz, Benjamin Miller, Binh Tang, Bowen Shi, Brian Karrer, Candace Ross, Daniel Li (FAIR), Gargi Ghosh, Jacob Xu, Lili Yu, Luke Zettlemoyer, Maryam Fazel-Zarandi, Olga Golovneva, Ram Pasunuru, Russ Howes, Shelly Sheynin, Tianlu Wang, Uriel Singer, Vasu Sharma, Yaniv Taigman
July 14, 2023
June 05, 2023
NLP
Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering
Yung-Sung Chuang, Wei Fang, James Glass, Scott Yih, Daniel Li (FAIR)
June 05, 2023
October 14, 2022
NLP
SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning
Daniel Li (AI), Abdelrahman Mohamed, Annie Dong, Ching-Feng Yeh, Haibin Wu, Hung-yi Lee, Jiatong Shi, Kai-Wei Chang, Shinji Watanabe, Shu-Wen Yang, Tzu-Hsun Feng, Tzu-Quan Lin, Xuankai Chang, Zili Huang
October 14, 2022
May 22, 2022
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities
Annie Dong, Abdelrahman Mohamed, Shang-Wen Li, Andy T. Liu, Harry Chang, Hung-yi Lee, Jeff Lai, Jiatong Shi, Kushal Lakhotia, Phil Hall, Ray Chen, Sean Tsai, Shinji Watanabe, Shu-Wen Yang, Wenchin Huang, Xuankai Chang, Zili Huang
May 22, 2022
Our approach
Latest news
Foundational models
Meta © 2026