Li Jing 靖礼

Facebook AI Research (FAIR)

Email: ljng at fb dot com

Google Scholar | GitHub | Linkedin | Twitter


Li Jing is a postdoctoral researcher at Facebook AI Research (FAIR), working with Yann LeCun. Before joining FAIR, he obtained his PhD in physics from MIT. He received a BS in physics and a BA in economics from Peking University. He is a co-founder of Lightelligence Inc..
His current research focuses on self-supervised learning. He is also interested in representation learning, multimodal learning, AI for science.
He has been awarded Forbes China 30 under 30. He has won a gold medal in the 2010 International Physics Olympiad (IPhO).

Selected Projects

Self-supervised Learning

Understanding Dimensional Collapse in Contrastive Self-supervised Learning
Li Jing, Pascal Vincent, Yann LeCun, Yuandong Tian
to appear

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations
Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljacic
to appear

Barlow Twins: Self-Supervised Learning via Redundancy Reduction
Jure Zbontar*, Li Jing*, Ishan Misra, Yann LeCun, Stephane Deny
ICML 2021
[Paper] [Code] [Talk]

Implicit Rank-Minimizing Autoencoder
Li Jing, Jure Zbontar, Yann LeCun
NeurIPS 2020
[Paper] [Code] [Talk]

AI for Science

Deep learning enabled self-adaptive invisibility cloak
Chao Qian, Bin Zheng, Yichen Shen, Li Jing, Erping Li, Lian Shen, Hongsheng Chen
Nature Photonics 2020
[Paper] [News]

Heuristic Recurrent Algorithms for Photonic Ising Machines
Charles Roques-Carmes, Yichen Shen, Cristian Zanoci, Mihika Prabhu, Fadi Atieh, Li Jing, Tena Dubcek, Vladimir Ceperic, John Joannopoulos, Dirk Englund, Marin Soljacic
Nature Communications 2020
[Paper] [News]

Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks
John Peurifoy, Yichen Shen, Li Jing, Yi Yang, Fidel Cano-Renteria, Brendan Delacy, John Joannopoulos, Max Tegmark, Marin Soljacic
Science Advances 2018
[Paper] [News] [Code]

Recurrent neural networks and NLP

We Can Explain Your Research in Layman’s Terms: Towards Automating Science Journalism at Scale
Rumen Dangovski,Michelle Shen, Dawson Byrd, Li Jing, Desislava Tsvetkova, Preslav Nakov, Marin Soljacic
AAAI 2021

Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications
Matthew Khoury, Rumen Dangovski, Longwu Ou, Preslav Nakov, Yichen Shen, Li Jing
EMNLP 2020

Rotational Unit of Memory: A Novel Representation Unit for RNNs with Scalable Applications
Rumen Dangovski*, Li Jing*, Marin Soljacic
TACL (presented at NAACL) 2019
[Paper] [News] [Code]

Gated Orthogonal Recurrent Units: On Learning to Forget
Li Jing*, Caglar Gulcehre*, John Peurifoy, Yichen Shen, Max Tegmark, Marin Soljacic, Yoshua Bengio
Neural Computation 2019
[Paper] [Code]

Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs
Li Jing*, Yichen Shen*, Tena Dubcek, John Peurifoy, Scott Skirlo, Yann LeCun, Max Tegmark, Marin Soljacic
ICML 2017
[Paper] [Code] [Talk]