About

I am working at xAI, where I've contributed to Grok 2, 3, and 4.

I completed my Ph.D. at Princeton University in 2024, advised by Prof. Danqi Chen. I received an M.S. from UIUC and a B.S. from Peking University.

Papers     (show full / show selected)

• 

  Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training

  Zexuan Zhong, Mengzhou Xia, Danqi Chen, Mike Lewis

  COLM 2024

  Paper

• 

  REST: Retrieval-based Speculative Decoding

  Zhenyu He*, Zexuan Zhong*, Tianle Cai*, Jason D Lee, Di He

  NAACL 2024

  Paper | Code

• 

  Reliable, Adaptable, and Attributable Language Models with Retrieval

  Akari Asai, Zexuan Zhong, Danqi Chen, Pang Wei Koh, Luke Zettlemoyer, Hannaneh Hajishirzi, Wen-tau Yih

  arXiv 2024

  Paper

• 

  MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

  Zexuan Zhong*, Zhengxuan Wu*, Christopher D Manning, Christopher Potts, Danqi Chen

  EMNLP 2023

  Paper | Code

• 

  Poisoning Retrieval Corpora by Injecting Adversarial Passages

  Zexuan Zhong*, Ziqing Huang*, Alexander Wettig, Danqi Chen

  EMNLP 2023

  Paper | Code

• 

  Privacy Implications of Retrieval-Based Language Models

  Yangsibo Huang, Samyak Gupta, Zexuan Zhong, Kai Li, Danqi Chen

  EMNLP 2023

  Paper | Code

• 

  Retrieval-based Language Models and Applications

  Akari Asai, Sewon Min, Zexuan Zhong, Danqi Chen

  ACL 2023 (Tutorial)

  Paper | Videos | Website

• 

  Should You Mask 15% in Masked Language Modeling?

  Alexander Wettig*, Tianyu Gao*, Zexuan Zhong, Danqi Chen

  EACL 2023

  Paper | Code

• 

  Training Language Models with Memory Augmentation

  Zexuan Zhong, Tao Lei, Danqi Chen

  EMNLP 2022

  Paper | Code

• 

  Recovering Private Text in Federated Learning of Language Models

  Samyak Gupta*, Yangsibo Huang*, Zexuan Zhong, Tianyu Gao, Kai Li, Danqi Chen

  NeurIPS 2022

  Paper | Code

• 

  Structured Pruning Learns Compact and Accurate Models

  Mengzhou Xia, Zexuan Zhong, Danqi Chen

  ACL 2022

  Paper | Code

• 

  Simple Entity-Centric Questions Challenge Dense Retrievers

  Christopher Sciavolino*, Zexuan Zhong*, Jinhyuk Lee, Danqi Chen

  EMNLP 2021

  Paper | Code

• 

  A Frustratingly Easy Approach for Entity and Relation Extraction

  Zexuan Zhong, Danqi Chen

  NAACL 2021

  Paper | Code

• 

  Factual Probing Is [MASK]: Learning vs. Learning to Recall

  Zexuan Zhong*, Dan Friedman*, Danqi Chen

  NAACL 2021

  Paper | Code

• 

  Robustra: Training Provable Robust Neural Networks over Reference Adversarial Space

  Linyi Li*, Zexuan Zhong*, Bo Li, Tao Xie

  IJCAI 2019

  Paper

• 

  Learning Food Quality and Safety using Wireless Stickers

  Unsoo Ha, Yunfei Ma, Zexuan Zhong, Tzu-Ming Hsu, Fadel Adib

  HotNets 2018

  Paper

• 

  SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications

  Zexuan Zhong, Jiaqi Guo, Wei Yang, Jian Peng, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang

  EMNLP 2018

  Paper

• 

  CoLink: An Unsupervised Framework for User Identity Linkage

  Zexuan Zhong, Yong Cao, Mu Guo, Zaiqing Nie

  AAAI 2018

  Paper

• 

  Generating Regular Expressions from Natural Language Specifications: Are We There Yet?

  Zexuan Zhong, Jiaqi Guo, Wei Yang, Tao Xie, Jian-Guang Lou, Ting Liu, Dongmei Zhang

  AAAI 2018 NLP4SE

  Paper

Experience

• 2023.6 - 2023.12, Research Intern, Meta
  Mentor: Mike Lewis
• 2018.5 - 2018.8, Visiting Research Assistant, MIT Media Lab
  Advisor: Fadel Adib
• 2017.9 - 2019.5, Research Assistant, University of Illinois at Urbana-Champaign
  Advisor: Tao Xie
• 2016.7 - 2017.5, Research Intern, Microsoft Research Asia
  Mentor: Zaiqing Nie

Selected Honors

• J.P. Morgan PhD Fellowship, 2022
• Princeton SEAS Award for Excellence, 2022
• Siebel Scholar, 2019
• Programming Contests: ICPC World Finals in 2019; Gold Medals × 4 in Asian and North American regionals; First Prize in the China National Olympiad in Informatics 2012