Haizhong Zheng

Ph.D. Candidate

Computer Science and Engineering

University of Michigan, Ann Arbor

Email: hzzheng@umich.edu

[C.V.] [Scholar] [LinkedIn]

I am currently a Ph.D. candidate in the Department of Electrical Engineering and Computer Science at University of Michigan and advised by Prof. Atul Prakash. I received my B.S. and M.S. degree from Shanghai Jiao Tong University advised by Prof. Haojin Zhu.

I was a research intern in Lawrence Livermore National Laboratory (LLNL) in the summer of 2023, supervised by Dr. Bhavya Kailkhura on the topic of LLM inference efficiency. Previously, I was an Applied Scientist Intern mentored by Dr. Wei Ding and Dr. Qian Cui at AWS in the summer of 2021.

My research focuses on how to design more efficient machine learning algorithms:

  • LLM Inference Efficiency: How to teach LLMs to perform more efficient inference to balance the trade-off between performance and inference cost?
  • Data-Efficient Learning: How to train and fine-tune models using fewer data and labels, particularly leveraging the patterns already learned by pretrained models?

Selected Publications

Adaptive Skeleton Graph Decoding
Shuowei Jin*, Yongji Wu*, Haizhong Zheng, Qingzhao Zhang, Matthew Lentz, Z. Morley Mao, Atul Prakash, Feng Qian, Danyang Zhuo. Preprint [PDF]

Learn To be Efficient: Build Structured Sparsity in Large Language Models
Haizhong Zheng, Xiaoyan Bai, Beidi Chen, Fan Lai, Atul Prakash. Preprint [PDF]

Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation
Haizhong Zheng, Jiachen Sun, Shutong Wu, Bhavya Kailkhura, Z. Morley Mao, Chaowei Xiao, Atul Prakash. Preprint [PDF]

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
Jiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash, Z. Morley Mao, Chaowei Xiao. ICLR'2024 [PDF]

Coverage-centric Coreset Selection for High Pruning Rates
Haizhong Zheng, Rui Liu, Fan Lai, Atul Prakash. ICLR'2023 [PDF] [Code]

Efficient Adversarial Training with Transferable Adversarial Examples
Haizhong Zheng, Ziqi Zhang, Juncheng Gu, Honglak Lee, Atul Prakash. CVPR'2020 [PDF] [Code]

Analyzing the Interpretability Robustness of Self-Explaining Models
Haizhong Zheng, Earlence Fernandes, Atul Prakash. ICML'2019 (Workshop) [PDF]

Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks
Haizhong Zheng, Minhui Xue, Hao Lu, Shuang Hao, Haojin Zhu, Xiaohui Liang, Keith Ross. NDSS'2018 [PDF]

Work Experience

Research Intern, Lawrence Livermore National Laboratory (LLNL), Livermore, CA
May 2023 - Aug. 2023


Applied Scientist Intern, Amazon Web Servives (AWS), Inc., Seattle, WA
May 2021 - Aug. 2021


Teaching

Co-Lead Instuctor in EECS 598-012 (Machine Learning Security and Privacy)
University of Michigan, Winter 2023


Graduate Student Instuctor in EECS 281 (Data Structures and Algorithms)
University of Michigan, Fall 2021



Last updated: 2023.10