Welcome to Zeyi Wen's Homepage

Dr. Zeyi Wen is Assistant Professor at the Data Science and Analytics (DSA) Thrust of Information Hub at Hong Kong University of Science and Technology, Guangzhou (HKUST-GZ). Before joining HKUST-GZ, he was Lecturer at The University of Western Australia, Research Fellow at National University of Singapore and The University of Melbourne after PhD completion at The University of Melbourne. He obtained his Bachelor's Degree from South China University of Technology. Dr. Wen was a winner of Best Paper Award at IEEE Transactions on Parallel and Distributed Systems (TPDS) 2019. His research work has led to open-source ML systems including ThunderGBM Star and ThunderSVM Star. He is an Action Editor (AE) of MLOSS section for the Journal of Machine Learning Research (JMLR).

Dec 2024: Two papers on LLM inference and fine-tuning got accepted by AAAI'25.
Nov 2024: Our paper on GBDTs for High Dimensional Data was accepted by KDD'25.
Sep 2024: Our paper on SVMs for ABSA tasks was accepted by EMNLP'24 Findings.
Jun 2024: Our paper on Bayesian Network Learning was accepted by IEEE TPDS.
May 2024: Our paper on PGM inference acceleration was accepted by USENIX ATC'24.
Feb 2024: Our paper on Hyper-parameter Optimization with Adaptive Fidelity was accepted by CVPR'24.
Jan 2024: Our paper on Bandit-based Hyperparameter Optimization was accepted by ICDE'24.

Large Language Model Inference/Training/Fine-Tuning Acceleration
Machine Learning Systems, Automatic Machine Learning, and High-Performance Computing

Current Courses at HKUST-GZ

Past Courses at UWA

There is currently one PhD opening under Dr. Zeyi Wen's supervision. Students interested in efficiency optimization for Large Language Models (LLMs) can send their applications by email. An application should include a resume with transcript(s).

Current graduate students and their research

Name	Research
Guoli Wu (PhD student to start from Spring 2025)	LLM inference optimization
Haichao Fang (RBM MPhil student from Fall 2024)	LLMs for health applications
Chengxi Liao (PhD student since Fall 2024)	Long context LLM inference
Tong Yuan (PhD student since Fall 2024)	Distributed LLM inference
Ruijia Yang (PhD student since Fall 2024)	Efficient LLM inference
Rui Zhang (PhD student since Fall 2024)	Accelerating kernel machine training
Zeyuan Lin (Visiting MPhil student from Fall 2024)	Kernels for CNNs
Hangyu Yang (Visiting master student from Fall 2024)	Efficient fine-tuning for LLMs
Xinhao Huang (PhD student from Spring 2024)	Model decomposition
Youliang Huang (RBM MPhil student from Fall 2023)	Efficient fine-tuning for LLMs
Jihang Li (PhD student since Fall 2023)	Learning operator acceleration with GPUs
Minping Chen (PhD student since Fall 2023)	Efficient fine-tuning for LLMs
Yuebin Xu (PhD student since Fall 2023)	Hyper-parameter optimization (HPO) for LLMs
Xuemei Peng (PhD student since Spring 2023)	Efficient LLM serving
Yile Chen (Visiting PhD student since 2022)	Hyper-parameter optimization (HPO)
Hanfeng Liu (PhD student since Fall 2022)	Parallel GBDT training