Shuai Zhang
Assistant Professor, Data Science
2117 Guttenberg Information Technologies Center (GITC)
About Me
I am an assistant professor in the Department of Data Science, New Jersey Institute of Technology (NJIT), starting at Fall 2023. I earned my Ph.D. in Electrical and Computer Engineering from Rensselaer Polytechnic Institute under the supervision of Dr. Meng Wang. Previously, I was fortunately to work with IBM Thomas J. Watson Research Center and MIT-IBM Watson AI Lab.
Education
Ph.D.
; Rensselaer Polytechnic Institute
; Electrical and Computer Engineering
; 2021
B.E. ; University of Science and Technology of China ; ; 2016
B.E. ; University of Science and Technology of China ; ; 2016
2025 Fall Courses
DS 488 - INDEPENDENT STUDY IN DS
DS 726 - INDEPENDENT STUDY II
DS 675 - MACHINE LEARNING
DS 700B - MASTER'S PROJECT
DS 725 - INDEPENDENT STUDY I
DS 701C - MASTER'S THESIS
DS 790A - DOCT DISSERTATION & RES
DS 792B - PRE-DOCTORAL RESEARCH
CS 792 - PRE-DOCTORAL RESEARCH
DS 701B - MASTER'S THESIS
DS 726 - INDEPENDENT STUDY II
DS 675 - MACHINE LEARNING
DS 700B - MASTER'S PROJECT
DS 725 - INDEPENDENT STUDY I
DS 701C - MASTER'S THESIS
DS 790A - DOCT DISSERTATION & RES
DS 792B - PRE-DOCTORAL RESEARCH
CS 792 - PRE-DOCTORAL RESEARCH
DS 701B - MASTER'S THESIS
Past Courses
CS 732: ADVANCED MACHINE LEARNING
DS 675: MACHINE LEARNING
DS 675: MACHINE LEARNING
Research Interests
My research has been focused on the theoretical foundations of deep learning and the design of principled and fast algorithms for better, safer, and more efficient AI applications. My current research focuses on the theoretical foundation of foundation models and parameter-efficient transfer learning.
Journal Article
Xiaobing Chen, Boyang Zhang, Xiangwei Zhou, Mingxuan Sun, Shuai Zhang, Songyang Zhang, Geoffrey Ye Li.
2025. "Efficient Training of Large-Scale AI Models Through Federated Mixture-of-Experts: A System-Level Approach."
arXiv preprint arXiv:2507.05685 .
Yubo Huang, Xin Lai, Muyang Ye, Anran Zhu, Zixi Wang, Jingzehua Xu, Shuai Zhang, Zhiyuan Zhou, Weijie Niu. 2025. "LHQ-SVC: Lightweight and High Quality Singing Voice Conversion Modeling." ICASSP, 2025 .
Yimian Ding, Jingzehua Xu, Guanwen Xie, Shuai Zhang, Yi Li. 2025. "Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks." IROS, 2025 .
Guanwen Xie, Jingzehua Xu, Yimian Ding, Zhi Zhang, Shuai Zhang, Yi Li. 2025. "Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions." IROS, 2025 .
Jingzehua Xu, Guanwen Xie, Zekai Zhang, Xiangwang Hou, Shuai Zhang, Yong Ren, Dusit Niyato. 2025. "UPEGSim: An RL-Enabled Simulator for Unmanned Underwater Vehicles Dedicated in the Underwater Pursuit-Evasion Game." IEEE Internet of Things Journal , vol. 12 , no. 3 , pp. 2334--2346.
Yubo Huang, Xin Lai, Muyang Ye, Anran Zhu, Zixi Wang, Jingzehua Xu, Shuai Zhang, Zhiyuan Zhou, Weijie Niu. 2025. "LHQ-SVC: Lightweight and High Quality Singing Voice Conversion Modeling." ICASSP, 2025 .
Yimian Ding, Jingzehua Xu, Guanwen Xie, Shuai Zhang, Yi Li. 2025. "Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks." IROS, 2025 .
Guanwen Xie, Jingzehua Xu, Yimian Ding, Zhi Zhang, Shuai Zhang, Yi Li. 2025. "Never too Prim to Swim: An LLM-Enhanced RL-based Adaptive S-Surface Controller for AUVs under Extreme Sea Conditions." IROS, 2025 .
Jingzehua Xu, Guanwen Xie, Zekai Zhang, Xiangwang Hou, Shuai Zhang, Yong Ren, Dusit Niyato. 2025. "UPEGSim: An RL-Enabled Simulator for Unmanned Underwater Vehicles Dedicated in the Underwater Pursuit-Evasion Game." IEEE Internet of Things Journal , vol. 12 , no. 3 , pp. 2334--2346.
SHOW MORE
Conference Proceeding
"Mixture-of-Experts for Distributed Edge Computing with Channel-Aware Gating Function"
2025.
"On the Training Dynamics of Contrastive Learning with Imbalanced Feature Distributions: A Theoretical Study of Feature Learning"
2025.
"Theoretical Guarantees and Training Dynamics of Contrastive Learning: How Misaligned Data Influence Feature Purity"
2025.
"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers"
2025.
"Learning on transformers is provable low-rank and sparse: A one-layer analysis"
2024.
2025.
"On the Training Dynamics of Contrastive Learning with Imbalanced Feature Distributions: A Theoretical Study of Feature Learning"
2025.
"Theoretical Guarantees and Training Dynamics of Contrastive Learning: How Misaligned Data Influence Feature Purity"
2025.
"When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers"
2025.
"Learning on transformers is provable low-rank and sparse: A one-layer analysis"
2024.
SHOW MORE
Conference Paper
"Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning"
ICML 2024, 2024.
"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks "
ICLR, January (1st Quarter/Winter), 2023.
"How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis"
ICLR, 2022.
"Why lottery ticket wins? a theoretical perspective of sample complexity on sparse neural networks"
Advances in Neural Information Processing Systems (NeurIPS), 2021.
"Fast learning of graph neural networks with guaranteed generalizability: one-hidden-layer case"
International Conference on Machine Learning (ICML), 2020.
ICML 2024, 2024.
"Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks "
ICLR, January (1st Quarter/Winter), 2023.
"How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis"
ICLR, 2022.
"Why lottery ticket wins? a theoretical perspective of sample complexity on sparse neural networks"
Advances in Neural Information Processing Systems (NeurIPS), 2021.
"Fast learning of graph neural networks with guaranteed generalizability: one-hidden-layer case"
International Conference on Machine Learning (ICML), 2020.
Other
"Non-Convex Optimizations for Machine Learning with Theoretical Guarantee: Robust Matrix Completion and Neural Network Learning"
Rensselaer Polytechnic Institute, 2021.
Rensselaer Polytechnic Institute, 2021.