Haizhong Zheng

Ph.D. Candidate

Computer Science and Engineering

University of Michigan, Ann Arbor

Email: hzzheng@umich.edu

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

I am a final-year Ph.D. student advised by Prof. Atul Prakash at University of Michigan. I am also working closely with Prof. Beidi Chen at Carnegie Mellon University. I received my B.S. and M.S. degree from Shanghai Jiao Tong University, where I was 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.

Research Interests: Hardware-aware efficient models training, machine learning system, and data efficiency algorithm.

My research focuses on building models, algorithms, and systems for scalable and efficient ML, which aims to bridge the gap between the rapid scaling of models and the slower scaling of hardware and high-quality data. In particular, my work has been along two lines: (1) Designing and training hardware-aware and system-aware models for fast model inference. (2) Designing algorithms for efficient data selection, augmentation, and annotation.

Selected Publications

ELFS: Enhancing Label-Free Coreset Selection via Clustering-based Pseudo-Labeling
Haizhong Zheng*, Elisa Tsai*, Yifu Lu, Jiachen Sun, Brian R. Bartoldson, Bhavya Kailkhura, Atul Prakash. Preprint [PDF]

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]

* indicates equal contribution.

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


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: 2024.6