Haizhong Zheng
Postdoctoral Researcher
Electrical and Computer Engineering
Carnegie Mellon University
Ph.D. @ UMich
Email: hzzheng@umich.edu
I am a postdoctoral researcher at InfiniAI Lab advised by Prof. Beidi Chen at Carnegie Mellon University. I am also a member of Catalyst Group at CMU. I received my Ph.D. degree from University of Michigan and was advised by Prof. Atul Prakash. Before that, I obtained my B.S. and M.S. degree from Shanghai Jiao Tong University, where I was advised by Prof. Haojin Zhu.
Research Interests: Hardware-aware efficient models, machine learning system, and data efficiency algorithm.
My research focuses on building models, algorithms, and systems for scalable and efficient ML. The goal is 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 human feedback.
Selected Publications
Adaptive Skeleton Graph Decoding
[PDF]
Shuowei Jin*, Yongji Wu*, Haizhong Zheng, Qingzhao Zhang, Matthew Lentz, Z. Morley Mao, Atul Prakash, Feng Qian, Danyang Zhuo.
Preprint
ELFS: Label-Free Coreset Selection with Proxy Training Dynamics
[PDF]
Haizhong Zheng*, Elisa Tsai*, Yifu Lu, Jiachen Sun, Brian R. Bartoldson, Bhavya Kailkhura, Atul Prakash.
International Conference on Learning Representations (ICLR), 2025
Harmful Terms and Where to Find Them: Measuring and Modeling Unfavorable Financial Terms and Conditions in Shopping Websites at Scale
[PDF]
Elisa Tsai, Neal Mangaokar, Boyuan Zheng, Haizhong Zheng, Atul Prakash.
The Web Conference (WWW), 2025 (Oral)
Learn To be Efficient: Build Structured Sparsity in Large Language Models
[PDF]
Haizhong Zheng, Xiaoyan Bai, Xueshen Liu, Z. Morley Mao, Beidi Chen, Fan Lai, Atul Prakash.
Advances in Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)
Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation
[PDF]
Haizhong Zheng, Jiachen Sun, Shutong Wu, Bhavya Kailkhura, Z. Morley Mao, Chaowei Xiao, Atul Prakash.
European Conference on Computer Vision (ECCV), 2024
CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
[PDF]
Jiachen Sun, Haizhong Zheng, Qingzhao Zhang, Atul Prakash, Z. Morley Mao, Chaowei Xiao.
International Conference on Learning Representations (ICLR), 2024
Coverage-centric Coreset Selection for High Pruning Rates
[PDF]
[Code]
Haizhong Zheng, Rui Liu, Fan Lai, Atul Prakash.
International Conference on Learning Representations (ICLR), 2023
Efficient Adversarial Training with Transferable Adversarial Examples
[PDF]
[Code]
Haizhong Zheng, Ziqi Zhang, Juncheng Gu, Honglak Lee, Atul Prakash.
Conference on Computer Vision and Pattern Recognition (CVPR), 2020
Analyzing the Interpretability Robustness of Self-Explaining Models
[PDF]
Haizhong Zheng, Earlence Fernandes, Atul Prakash.
International Conference on Machine Learning (ICML) Workshop, 2019
Smoke Screener or Straight Shooter: Detecting Elite Sybil Attacks in User-Review Social Networks
[PDF]
Haizhong Zheng, Minhui Xue, Hao Lu, Shuang Hao, Haojin Zhu, Xiaohui Liang, Keith Ross.
Network and Distributed System Security (NDSS), 2018
* indicates equal contribution.
Work Experience
Teaching
Last updated: 2025.1