Zekai Li | National Univeristy of Singapore

About Me

I am an undergraduate student at the National University of Singapore. I’m interested in efficient machine learning, such as dataset distillation, parameter generation, etc. I’m honored to be supervised by Dr. Kai Wang and Professor Yang You at NUS HPC-AI Lab. I have done research internships remotely at University of Toronto (advised by professor Konstantinos N Plataniotis) and Carnegie Mellon University (advised by professor Alexander Hauptmann and Dr. Zhi-Qi Cheng).

Prior to that, I was a member at NUS WING supervised by Professor Min-Yen Kan on my UROP.

Research Interests

Efficient Deep Learning: dataset distillation, model compression
Generative Models: parameter generation
Natural Language Processing: question-answering, LLM factuality and unlearning

Research Experience

Carnegie Mellon University [June 2024 - October 2024]: Research Internship. Advisors: Professor Alexander Hauptmann and Dr. Zhi-Qi Cheng.
University of Toronto [March 2024 - June 2024]: Research Internship. Advisors: Professor Konstantinos N Plataniotis.
NUS HPC-AI Lab [November 2023 - Ongoing]: Research Assistant. Advisors: Professor Yang You and Dr. Kai Wang.
NUS Web/IR Group [May 2023 - February 2024]: Undergraduate Research Opportunity Program. Advisors: Professor Kan Min-Yen and Dr. Yanxia Qin.

News

[Oct. 2023] I’ve joined NUS HPC-AI Lab as a research assistant supervised by Professor Yang You and Dr. Kai Wang.
[May. 2023] I’ve joined NUS WING as an undergraduate researcher supervised by Professor Kan Min-Yen [Feb. 2023] My paper on multi-hop question answering is accepted to ICASSP 2023.

Recent Publications

* Equal Contribution

Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios

Kai Wang*, Zekai Li*, Zhiqi Cheng, Samir Khaki, Ahmad Sajedi, Ramakrishna Vedantam, Konstantinos N Plataniotis, Alexander Hauptmann, and Yang You

PDF Code Under Review

Prioritize Alignment in Dataset Distillation

Zekai Li*, Ziyao Guo*, Wangbo Zhao, Tianle Zhang, Zhi-Qi Cheng, Samir Khaki, Kaipeng Zhang, Ahmad Sajedi, Konstantinos N Plataniotis, Kai Wang, Yang You

PDF Code Under Review

A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

Kai Wang, Yukun Zhou, Mingjia Shi, Zekai Li, Zhihang Yuan, Yuzhang Shang, Xiaojiang Peng, Hanwang Zhang, Yang You

PDF Code Under Review

ICASSP

Self-Adaptive Reasoning on Sub-Questions for Multi-Hop Question Answering

Zekai Li, Wei Peng

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023.

PDF Accept (Poster)

See full publication list on Google Scholar