Xian Li
RESEARCH SCIENTIST | MENLO PARK, UNITED STATES
Xian Li is a Research Scientist at FAIR. Her research interests center around scalable training methods for foundation models. She has worked on various research topics including machine translation, large language models, efficient architecture, synthetic data, self-improving algorithms for reasoning, alignment and agent.
Research Areas
Xian's Publications
November 30, 2022
HUMAN & MACHINE INTELLIGENCE
NLP
ToKen: Task Decomposition and Knowledge Infusion for Few-Shot Hate Speech Detection
Badr Alkhamissy, Asli Celikyilmaz, Lambert Mathias, Mona Diab, Pascale Fung, Srini Iyer, Ves Stoyanov, Xian Li, Zornitsa Kozareva, Faisal Ladhak
November 30, 2022
December 21, 2021
Improving Zero-Shot Translation by Disentangling Positional Information
James Cross, Paco Guzmán, Xian Li, Danni Liu, Jan Niehues
December 21, 2021
December 06, 2021
NLP
Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modeling
Hongyu Gong, Yun Tang, Juan Pino, Xian Li
December 06, 2021
August 01, 2021
Gender bias amplification during Speed-Quality optimization in Neural Machine Translation
Adi Renduchintala, Kenneth Heafield, Mona Diab, Xian Li, Denise Diaz
August 01, 2021
October 26, 2020
RESEARCH
SPEECH & AUDIO
Deep Multilingual Transformer with Latent Depth
Xian Li, Asa Cooper Stickland, Xiang Kong, Yuqing Tang
October 26, 2020
November 25, 2019
August 15, 2019
RESEARCH
SPEECH & AUDIO
On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models
August 15, 2019
Our approach
Latest news
Foundational models
Meta © 2025