Yezi Liu

profile_photo_cube.jpg

About me

I’m a Ph.D. candidate in the Department of Electrical Engineering and Computer Science at the University of California, Irvine (UCI), advised by Prof. Mohsen Imani. Before that, I did my M.S. in Computer Science at Texas A&M University with Prof. Xia “Ben” Hu and worked on knowledge-graph error detection and trustworthy data mining.

My research sits at the intersection of trustworthy & efficient graph learning/ML and LLM reasoning. I build methods that (i) unlearn data-specific information or de-bias models without full retraining/fine-tuning, (ii) make graph learning and hyperdimensional computing (HDC) more fair and robust, and (iii) enable LLMs to support efficient fine-tuning and low-resource inference.

Recently, I’ve been working on (first-authored):

News

  • Oct. 2025: One paper has been accepted by WSDM 2026. See you in Boise!

  • Aug. 2025: One paper has been accepted by CIKM 2025. See you in South Korea!

  • July 2025: One paper has been accepted by ACM Multimedia 2025! See you in Ireland!

  • May 2025: One paper has been accepted by TMLR.

  • April 2025: One paper has been accepted by IJCAI 2025. See you in Canada!

  • Jan. 2025: Two papers have been accepted by The Web Conference 2025. See you in Australia!

  • Oct. 2024: Two papers have been accepted by WACV 2025. See you in Tucson!

  • Aug. 2024: One paper has been accepted by ECCV 2024. See you in Italy!

  • May 2024: One paper has been accepted by EUSIPCO 2024. See you in France!

  • Aug. 2023: One paper has been accepted by CIKM 2023. See you in the United Kingdom!

  • May 2023: One paper has been accepted by EUSIPCO 2023. See you in Finland!

  • Aug. 2022: One paper has been accepted by CIKM 2022. See you in Atlanta!

Education

  • Ph.D. in Computer Engineering, University of California, Irvine, 2021 – 2026 (expected)

  • M.S. in Computer Science, Texas A&M University, 2019 – 2021

  • M.S. in Information Science, University of Pittsburgh, 2017 – 2019

Publications

Please refer to the Publications page or my Google Scholar.