Hong Kong University of Science and Technology
2025 – 2028 (expected)
Ph.D. in Industrial Engineering and Decision Analytics
- Advisor: Prof. Jiheng Zhang
Zean Han
Ph.D. Student at HKUST
Hong Kong University of Science and Technology
Advised by Jiheng Zhang
I work on the intersection of theory and industrial applications of modern AI, trying to bring learning theory to real-world applications.
About Me
I am a Ph.D. student in Industrial Engineering and Decision Analytics at the Hong Kong University of Science and Technology, where I am fortunate to be supervised by Prof. Jiheng Zhang, head and full professor of the department. My research develops theory and algorithms for real-world scenarios including LLM inference and offline-to-online learning. I am also interested in applying learning theory to management problems such as inventory management and dynamic pricing. My work often leverages tools from queueing theory, reinforcement learning, and optimization to study how complex service and decision systems behave under uncertainty.
Before coming to HKUST, I received my M.Phil degree in Pure Mathematics from the Chinese University of Hong Kong, where I spent two wonderful years working on geometric representation theory. I used to enjoy considering all kinds of geometric problems and trying to find the underlying algebraic structures. I worked on perverse sheaves and hypertoric varieties there. I am keen in running, watching movies and classical guitar.
Research Interest
- Efficient LLM Inference
- Offline-to-Online Learning
- Dynamic Pricing and Revenue Management
Broadly, I try to optimize decision systems under uncertainty using queueing theory, reinforcement learning, and optimization. I am also drawn to AI research which does not involve too much theoretical analysis.
Education
The Chinese University of Hong Kong
2023 – 2025
M.Phil in Pure Mathematics
- Research focus: geometric representation theory
- GPA: 3.81 / 4.0
Papers
Published
VoCAPTER: Voting-based Pose Tracking for Category-level Articulated Object via Inter-frame Priors
Li Zhang*, Zean Han*, Yan Zhong, Qiaojun Yu, Xingyu Wu, Xue Wang, Rujing Wang (*equal contribution)
Working papers
Geometry-Aware Offline-to-Online Learning in Linear Contextual Bandits
Zean Han, Ruihan Lin, Zezhen Ding, and Jiheng Zhang
Large-Scale LLM Inference with Heterogeneous Workloads: Prefill-Decode Contention and Asymptotically Optimal Control
Ruihan Lin, Zean Han, Zezhen Ding, and Jiheng Zhang
Learning to price and stock under contextual and censored demand
Zean Han, Zezhen Ding, and Jiheng Zhang