Welcome. I am a third year Ph.D. student at University of California, San Diego advised by Prof. Jingbo Shang. Before that, I received my B.S. in Computer Science at University of Illinois Urbana Champaign. You can find my CV here.

Research Interests

My research aims to address Natural Language Processing tasks with (extremely) weak supervision. I strive to answer the following questions:

• What knowledge do pre-trained neural language models encode? Is the current fine-tuning or prompting paradigm the best to distill the right part of these knowledge to domain-specific tasks?
• What is the best forms of getting supervision from human? How to inform machines about the NLP task goals with minimum human effort?
• Can machines go beyond extracting information to discovering novel information to expand human knowledge?

You can find my publications here.

Experience

• Microsoft Research, 2022.6 - 2022.9
  • Research Intern
  • Working on efficient fine-tuning of large language models.
• Adobe, 2021.6 - 2021.9
  • Research Intern.
  • Worked with Dr. Tong Sun and Dr. Jiuxiang Gu on efficient transformers and proposed an adaptive axis attention pattern.
• University of Pennsylvania, 2019.5 - 2019.8
  • Research Assistant.
  • Worked with Prof. Dan Roth on low-resource, cross-lingual named entity recognition. We also analyzed the effectiveness of Multilingual BERT.
• University of Illinois at Urbana-Champaign, 2018.12 - 2019.
  • Research Assistant.
  • Worked with Prof. Jiawei Han on TextCubes, Topic Extraction, and Representation Learning.

Invited Talks

• Jan 2022, On Cross-Lingual Ability of Multilingual BERT, at Google N2Formal.
• Jan 2021, On Extending Multilingual BERT, at University of Colorado Boulder.

Selected Awards

• Bronze Medal, ICPC World Finals @ Moscow (2021)
  • 2nd in North America, 11/118 worldwide
• UCSD Halıcıoğlu Data Science Fellowship (2020-2023)
• UCSD Jacob School of Engineering Fellowship (2020-2021)
• World Champion, IEEE Xtreme 13.0 (2019)
• UIUC Jeffry P. Blahut Memorial Scholarship (2018)

Leadership & Teaching

• Co-Coach for UCSD ICPC club (2020-Present), website here
  • coach and teach students for algorithmic programming contests.
  • UCSD ranked third in the SoCal Regional in Feb, 2022, Congratulations!

Visits, Collaborations & Questions

• If you are going to visit UCSD, please let me buy you a bubble tea 🧋(or coffee☕)*.
• I am warm-heartedly open to any discussion related to natural language processing and machine learning in general.
• For undergraduate students, I am happy to answer questions about:
  • Grad School or Industry
  • Research in NLP
  • Competitive Programming
• and if you have interest to conduct research in NLP, I am happy to collaborate.

Email is usually the best way to contact me.

*This is a copy-pasta from Liyuan Liu, who introduced me to NLP research.