I am an Assistant Professor in Computer Science & Engineering (CSE) Department, Washington University in St. Louis (WashU). I received my Ph.D. degree in Computer Science Department, UIUC, advised by Prof. Jiawei Han. After that, I visited UW as a researcher and worked with Prof. Hanna Hajishirzi. Prior to UIUC, I received my Bachelor Degree in Electronic Engineering in Tsinghua University in 2018. My research interest broadly lies in the intersection of natural language processing and machine learning, and I am especially interested in understanding the properties of language models as well as improving their trustworthiness and efficiency.

I am looking for PhD students for 25’Fall and interns year-round! If you are interested in working with me, please fill in this form . While submitting the form is already sufficient, you are also welcome to reach out to me via email. I will read every email but please understand that I might not be able to respond to each of them due to time constraints.

If you are applying for CSE PhD for 25’Fall, application fee could be waived through attending the PhD information sessions under the Computer Science & Engineering category.

Recent Research Interests

• Large Language Model Factuality: I build methods for integrating factual knowledge within language models, including graphs(1), ontologies(1,2,3), entities(1,2), and applying them for downstream tasks(1) in low-resource setting.
• Large Language Model Reasoning: I investigate how large language model generations can self-improve their reasoning abilities (unsupervised self-improving reasoning, weakly-supervised reasoning).
• Large Language Model Alignment: I work on improving language model calibration to align their confidence with performance, see our recent work on reward calibration in RLHF.
• Training and Inference Efficiency of Large Language Models: I work on improving language model training and inference efficiency, see our recent work on long in-context learning.
• Data Efficiency for Language Model Training: I study how to better fine-tune language model with limited training data, including data self-generation(1,2,3), denoising distant-supervision and integrating metadata.
• Representation Learning: I study how the text embedding space could be regularized in different circumstances (category-based, joint-categories learning, contextualized, etc.)

Honors and Awards

Microsoft Research PhD Fellowship 2021-2023
C.W. Gear Outstanding Graduate Award
Chirag Foundation Graduate Fellowship
Outstanding Graduates, Tsinghua University 2018
Academic Excellence Scholarship, Tsinghua University 2015-2017
China National Scholarship (Top 1%) 2016
Samsung Scholarship 2015

Education

• University of Illinois, Urbana-Champaign (2018.08-2023.12)
  Ph.D. in Computer Science
  Research Interest: Natural Language Processing, Data Mining Advisor: Prof. Jiawei Han

• Tsinghua University (2014.08-2018.07)
  B. Eng. in Electronic Engineering
  Advisor: Prof. Yong Li

• University of California, Los Angeles (2017.07-2017.09)
  CSST summer program
  Advisor: Prof. Wei Wang

Experience

• Google Core-ML (2022.06-2022.09)
  Research Intern
  Host: Dr. Le Hou and Dr. Yuexin Wu

• Google Research (2021.05-2021.08)
  Research Intern
  Host: Dr. Tianqi Liu and Dr. Jialu Liu

• Microsoft Research Redmond (2020.06-2020.09)
  Research Intern
  Host: Dr. Chunyuan Li and Krishan Subudhi