Zeliang Zhang

Ph.D. Student, University of Rochester

hust0426 @ gmail.com

Bio

I am a PhD student in the Department of Computer Science at the University of Rochester, advised by Prof. Chenliang Xu. I received my B.Eng. from CS Department, Huazhong University of Science and Technology in 2022. In my undergrad, I worked with Prof. Kun He and Mr. Xiaosen Wang at HUST on adversarial machine learning. I also work closely with Prof. Yijie Peng at PKU on gradient estimation (Zeroth-Order optimization), and Prof. Xiao-Yang Liu at RPI/Columbia on high-performance quantum and tensor computation. I am good at playing Erhu and familiar with Violin. Welcome to reach out to chat:)

I am broadly interested in:
- Trustworthy AI: security, privacy, and explainability;
- Optimization Theory: zeroth-order optimization, stochastic optimization;
- High-Performance Computaiton for AI: GPU tensor core, tensor computation;

Currently, I mainly work on efficient and reliable AI for my Ph.D. degree. I am also interested in the security issue of (MultiModal-)LLMs. 😀

News

Publications & Projects

Google Scholar.
* indicates equal contribution. The order of co-first author may be different from the literature.
indicates the project leader.

Forward Learning for Gradient-based Black-box Saliency Map Generation

Zeliang Zhang*†, Mingqian Feng*, Jinyang Jiang, Rongyi Zhu, Yijie Peng, Chenliang Xu

Preprint arXiv 2024.

Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training

Zeliang Zhang*†, Jinyang Jiang*, Zhuo Liu, Susan Liang, Yijie Peng, Chenliang Xu

Preprint arXiv 2024.

How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies

Edward Small, Wei Shao, Zeliang Zhang, Peihan Liu, Jeffrey Chan, Kacper Sokol, Flora Salim

Data Mining and Knowledge Discovery.

One Forward is Enough for Training Neural Networks via the Likelihood Ratio Method

Jinyang Jiang*, Zeliang Zhang*, Chenliang Xu, Zhaofei Yu, Yijie Peng

ICLR 2024.

Noise Optimization for Artificial Neural Networks

Li Xiao (Advisor), Zeliang Zhang, Jinyang Jiang, Yijie Peng

first CASE 2022, then IEEE Transactions on Automation Science and Engineering.

DHN: DEEP HAMILTONIAN NETWORK FOR VARIATIONAL REINFORCEMENT LEARNING

Zeliang Zhang, Yipeng Wang, Zeqi Liu, Xiao-Yang Liu

NIPS 2021 QTNML W.

Paper Adopted by the ElegantRL library (~ 3k stars! 🚀).

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers

Zeliang Zhang*, Mingqian Feng*, Zhiheng Li, Chenliang Xu

CVPR 2024.

Learning to Transform Dynamically for Better Adversarial Transferability

Rongyi Zhu*, Zeliang Zhang*†, Susan Liang, Zhuo Liu, Chenliang Xu

CVPR 2024.

Forward Learning with Differential Privacy

Mingqian Feng, Zeliang Zhang, Jinyang Jiang, Chenliang Xu

Coming Soon

Bag of Tricks to Boost the Adversarial Transferability

Zeliang Zhang*†, Rongyi Zhu*, Wei Yao, Xiaosen Wang, Chenliang Xu

Preprint arXiv 2024

Random Smooth-based Certified Defense against Text Adversarial Attack

Zeliang Zhang*†, Wei Yao*, Susan Liang, Chenliang Xu

Findings of EACL 2024.

Diversifying the High-level Features for better Adversarial Transferability

Zeliang Zhang*, Zhiyuan Wang*, Siyuan Liang, Xiaosen Wang

BMVC 2023.

Structure Invariant Transformation for better Adversarial Transferability

Xiaosen Wang, Zeliang Zhang, Jianping Zhang

ICCV 2023.

Triangle Attack: A Query-efficient Decision-based Adversarial Attack

Xiaosen Wang, Zeliang Zhang, Kangheng Tong, Dihong Gong, Kun He, Zhifeng Li, Wei Liu

ECCV 2022.

Video Understanding with Large Language Models: A Survey

Prof. Chenliang Xu and Prof. Jiebo Luo's Labs at URCS

TransferAttack

Trustworthy AI Group

Elegant RL

AI4Finance Foundation

RL for Quantum Circuits

AI4Finance Foundation

Classical Simulation of Quantum Circuits using Reinforcement Learning: Parallel Environments and Benchmark

Xiao-Yang Liu, Zeliang Zhang

NeurIPS dataset and benchmark track 2024.

Scalable CP Decomposition for Tensor Learning using GPU Tensor Cores

Zeliang Zhang, Zhuo Liu, Susan Liang, Zhiyuan Wang, Yifan Zhu, Chen Ding, Chenliang Xu

DAC 2024 WIP.

High-Performance Tensor Learning Primitives Using GPU Tensor Cores

Xiao-Yang Liu*, Zeliang Zhang*, Zhiyuan Wang, Han Lu, Xiaodong Wang, Anwar Walid

IEEE Transactions on Computers (CCF-A journal).

Trillion-Tensor: Trillion-Scale CP Tensor Decomposition

Zeliang Zhang, Xiao-Yang Liu, Pan Zhou

IJCAI 2020 TNRML W.

Parallel TTr1-Tensor: Randomized Compression-based Scheme for Tensor Train Rank-1 Decomposition

Zeliang Zhang, Junzhe Zhang, Guoping Lin, Zeyuan Yin, Kun He

NIPS 2020 QTNML W.

Discover and Mitigate Multiple Biased Subgroups in Image Classifiers

Zeliang Zhang*, Mingqian Feng*, Zhiheng Li, Chenliang Xu

CVPR 2024.

Learning to Transform Dynamically for Better Adversarial Transferability

Rongyi Zhu*, Zeliang Zhang*†, Susan Liang, Zhuo Liu, Chenliang Xu

CVPR 2024.

Forward Learning with Differential Privacy

Mingqian Feng, Zeliang Zhang, Jinyang Jiang, Chenliang Xu

Coming Soon

Forward Learning for Gradient-based Black-box Saliency Map Generation

Zeliang Zhang*†, Mingqian Feng*, Jinyang Jiang, Rongyi Zhu, Yijie Peng, Chenliang Xu

Preprint arXiv 2024.

Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training

Zeliang Zhang*†, Jinyang Jiang*, Zhuo Liu, Susan Liang, Yijie Peng, Chenliang Xu

Preprint arXiv 2024.

How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies

Edward Small, Wei Shao, Zeliang Zhang, Peihan Liu, Jeffrey Chan, Kacper Sokol, Flora Salim

Data Mining and Knowledge Discovery.

One Forward is Enough for Training Neural Networks via the Likelihood Ratio Method

Jinyang Jiang*, Zeliang Zhang*, Chenliang Xu, Zhaofei Yu, Yijie Peng

ICLR 2024.

Bag of Tricks to Boost the Adversarial Transferability

Zeliang Zhang*†, Rongyi Zhu*, Wei Yao, Xiaosen Wang, Chenliang Xu

Preprint arXiv 2024

Random Smooth-based Certified Defense against Text Adversarial Attack

Zeliang Zhang*†, Wei Yao*, Susan Liang, Chenliang Xu

Findings of EACL 2024.

Classical Simulation of Quantum Circuits using Reinforcement Learning: Parallel Environments and Benchmark

Xiao-Yang Liu, Zeliang Zhang

NeurIPS dataset and benchmark track 2024.

Diversifying the High-level Features for better Adversarial Transferability

Zeliang Zhang*, Zhiyuan Wang*, Siyuan Liang, Xiaosen Wang

BMVC 2023.

Structure Invariant Transformation for better Adversarial Transferability

Xiaosen Wang, Zeliang Zhang, Jianping Zhang

ICCV 2023.

Scalable CP Decomposition for Tensor Learning using GPU Tensor Cores

Zeliang Zhang, Zhuo Liu, Susan Liang, Zhiyuan Wang, Yifan Zhu, Chen Ding, Chenliang Xu

DAC 2024 WIP.

High-Performance Tensor Learning Primitives Using GPU Tensor Cores

Xiao-Yang Liu*, Zeliang Zhang*, Zhiyuan Wang, Han Lu, Xiaodong Wang, Anwar Walid

IEEE Transactions on Computers (CCF-A journal).

Triangle Attack: A Query-efficient Decision-based Adversarial Attack

Xiaosen Wang, Zeliang Zhang, Kangheng Tong, Dihong Gong, Kun He, Zhifeng Li, Wei Liu

ECCV 2022.

Noise Optimization for Artificial Neural Networks

Li Xiao (Advisor), Zeliang Zhang, Jinyang Jiang, Yijie Peng

first CASE 2022, then IEEE Transactions on Automation Science and Engineering.

Trillion-Tensor: Trillion-Scale CP Tensor Decomposition

Zeliang Zhang, Xiao-Yang Liu, Pan Zhou

IJCAI 2020 TNRML W.

Parallel TTr1-Tensor: Randomized Compression-based Scheme for Tensor Train Rank-1 Decomposition

Zeliang Zhang, Junzhe Zhang, Guoping Lin, Zeyuan Yin, Kun He

NIPS 2020 QTNML W.

DHN: DEEP HAMILTONIAN NETWORK FOR VARIATIONAL REINFORCEMENT LEARNING

Zeliang Zhang, Yipeng Wang, Zeqi Liu, Xiao-Yang Liu

NIPS 2021 QTNML W.

Paper Adopted by the ElegantRL library (~ 3k stars! 🚀).

Video Understanding with Large Language Models: A Survey

Prof. Chenliang Xu and Prof. Jiebo Luo's Labs at URCS

TransferAttack

Trustworthy AI Group

Elegant RL

AI4Finance Foundation

RL for Quantum Circuits

AI4Finance Foundation

Education

Experiences