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. He and Mr. Wang at HUST on adversarial machine learning. I also work closely with Prof. Peng at PKU on gradient estimation (Zeroth-Order optimization), and Prof. 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:)
Currently, I mainly work on efficient and reliable AI for my Ph.D. degree.
Email  / 
Google Scholar  / 
Github
|
|
[5/2024] |
I will work as a research intern at the deep learning group of Microsoft Research, Redmond. |
[1/2024] |
I will work as an Erhu performer at the Traditional Chinese Ensemble Group of Rochester. |
[10/2021] |
I will work as a research intern at the machine learning for sustainability group of Microsoft Research Asia, Beijing.
|
(* indicates the equal contribution with random author order. ‡ indicates the project leader.)
|
Understanding Model Ensemble in Transferable Adversarial Attack
Wei Yao*, Zeliang Zhang*, Huayi Tang, Yong Liu.
Preprint, 2024
We provide early theoretical insights that serve as a roadmap for advancing model ensemble adversarial attack.
|
|
Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
Zeliang Zhang, Zhuo Liu, Mingqian Feng, Chenliang Xu.
Findings of EMNLP, 2024
We empirically investigate the quantity bias in CLIP.
|
|
Do More Details Always Introduce More Hallucinations in LVLM-basedImage Captioning?
Mingqian Feng, Yunlong Tang, Zeliang Zhang, Chenliang Xu.
Preprint, 2024
To alleviate the problem of hallucinations, we propose the Differentiated Beam Decoding (DBD), along with a reliable new set of evaluation metrics: CLIP-Precision, CLIP-Recall, and CLIP-F1.
|
|
Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
Zeliang Zhang, Xiaodong Liu, Hao Cheng, Chenliang Xu, Jianfeng Gao.
Preprint, 2024
We propose a method of grouping and pruning similar experts to improve the model's parameter efficienc
|
|
Video Understanding with Large Language Models: A Survey
Yunlong Tang, Jing Bi, Siting Xu, Luchuan Song, Susan Liang, Teng Wang, Daoan Zhang, Jie An, Jingyang Lin, Rongyi Zhu, Ali Vosoughi, Chao Huang, Zeliang Zhang, Feng Zheng, Jianguo Zhang, Ping Luo, Jiebo Luo, Chenliang Xu.
Technical Report, 2023
This survey provides a detailed overview of the recent advancements in video understanding harnessing the power of LLMs.
|
|
Discover Multiple Biased Subgroups in Image Classifiers
Zeliang Zhang*, Mingqian Feng*, Zhiheng Li, Chenliang Xu.
CVPR, 2024
We propose a novel method, namely DII (decomposition, identification, and interpretation), to debug the multi-bias of the models.
|
|
Learning to Transform Dynamically for Better Adversarial Transferability
Rongyi Zhu*, Zeliang Zhang*‡, Susan Liang, Zhuo Liu, Chenliang Xu.
CVPR, 2024
We propose a novel method, namely L2T (learn to transform), to boost the adversarial transferability.
|
|
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
We explore the potential of Likelihood ratio method for gradient estimation and train multi-architectures of NN without back-propagation.
|
|
Bag of Tricks to Boost the Adversarial Transferability
Zeliang Zhang, Wei Yao, Xiaosen Wang
Technical Report, 2024
We propose a bag of novel tricks to boost the adversarial transferability among different models.
|
|
Random Smooth-based Certified Defense against Text Adversarial Attack
Zeliang Zhang*, Wei Yao*, Susan Liang, Chenliang Xu
EACL Findings, 2024
We propose to treat the word substitution as a continuous perturbation on the word embedding representation for better robustness.
|
|
Structure Invariant Transformation for better Adversarial Transferability
Xiaosen Wang, Zeliang Zhang, Jianping Zhang
ICCV, 2023
We propose a novel input transformation based attack, called Structure Invariant Transformation (SIA), which applies a random image transformation onto each image block to craft a set of diverse images for gradient calculation.
|
|
High-performance Tensor-Train Primitives Using GPU Tensor Cores
Xiao-Yang Liu, Hao Hong, Zeliang Zhang, Weiqing Tong, Xiaodong Wang, Anwar Walid
IEEE Transaction on Computers, 2024
We present high-performance tensor-train primitives using GPU tensor cores and demonstrate three applications.
|
|
Diversifying the High-level Features for better Adversarial Transferability
Zhiyuan Wang*, Zeliang Zhang*, Siyuan Liang, Xiaosen Wang
BMVC, 2023, oral
We propose diversifying the high-level features (DHF) for more transferable adversarial examples.
|
|
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, 2024
We quantitatively evaluate the robustness of fairness optimization strategies.
|
|
Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark
Xiao-Yang Liu, Zeliang Zhang
NeurIPS dataset and benchmark track, 2023
We develop a dozen of massively parallel environments to simulate quantum circuits. We open-source our parallel gym environments and benchmarks.
|
|
High-Performance Tensor Learning Primitives Using GPU Tensor Cores
Xiao-Yang Liu*, Zeliang Zhang*, Zhiyuan Wang, Han Lu, Xiaodong Wang, Anwar Walid.
IEEE Transaction on Computers, 2022
We propose novel hardware-oriented optimization strategies for tensor learning primitives on GPU tensor cores.
|
|
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
We propose a novel Triangle Attack (TA) to optimize the perturbation by utilizing the geometric information that the longer side is always opposite the larger angle in any triangle.
|
|
Noise Optimization for Artificial Neural Networks
Li Xiao, Zeliang Zhang, Yijie Peng
Short paper: CASE, 2022; Long paper: T-ASE, 2024
We propose a new technique to compute the pathwise stochastic gradient estimate with respect to the standard deviation of the Gaussian noise added to each neuron of the ANN.
|
|
University of Rochester , NY, USA
Ph.D. in Computer Science
Sep. 2022 - Present
Advisor: Chenliang Xu
|
|
Huazhong University of Science and Technology, Wuhan, China
B.Eng in Computer Science and Technology
Sept. 2018 - Jun. 2022
|
|
Microsoft Research , Redmond, US
Research intern, then part-time researcher
May 2024 - Present
Advisor: Xiaodong Liu and Hao Cheng
Work on efficient training and inference of language models.
|
|
Microsoft Research Asia , Beijing, China
Research intern
Oct. 2021 - Jun. 2022
Advisor: Xinran Wei
Work on high-performance computation of DFT, which is important/bottleneck in material design using AI.
|
|
Columbia University , NYC, US
Research assistant
Feb. 2020 - Dec. 2022
Advisor: Xiao-Yang Liu
Work on high-performance tensor computation using GPUs and publish two workshop papers on top conference, namely the "Trillion-Tensor: Trillion-Scale CP Tensor Decomposition" at IJCAI 2020 TNRML workshop and "Parallel TTr1-Tensor: Randomized Compression-based Scheme for Tensor Train Rank-1 Decomposition" at NIPS 2020 QTNML workshop.
|
|
Elegant RL (~ 3k stars! 🚀)
Develop the RL-Hamiltonian algorithm to stablize the RL training and publish it as a poster in NIPS 2021 QTNML workshop.
|
|
TransferAttack
One of the main contributors. TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.
|
|
RL for Quantum Circuits
One of the main contributors. Open-source benchmark and environments for the classical simulation of quantum circuits.
|
|