Hanzhe Liang

Shenzhen, China

Incoming Ph.D. Student, MBZUAI

lianghanzhe2023@email.szu.edu.cn

I am Hanzhe Liang, an incoming Ph.D. student in Computational Biology at MBZUAI, supervised by Jun Wen. Prior to that, I received my dual Bachelor’s degrees in Management and Science from Shenzhen University in June 2026 and also received reasearch training during my undergraduate study, where I was advised by Can Gao, Jinbao Wang, and Linlin Shen.

My research interests include anomaly detection, spatial intelligence, digital twins, and AI for precision medicine. I am particularly interested in building generalizable AI systems for industrial inspection and high-order biomedical prediction.

Experience

2026 – present — Ph.D. Student, Department of Computational Biology, MBZUAI
2026 – 2026 — Visiting Student, Department of Computational Biology, MBZUAI
2023 – 2025 — Research Assistantship, Computer Vision Institute and School of Artificial Intelligence, Shenzhen University
2023 – 2026 — Bachelor of Management and Bachelor of Science, Shenzhen University and Audencia

news

Jun 14, 2026	BinaryAD was accepted by Pattern Recognition.
May 14, 2026	MFF-M3AD was accepted by Neural Networks.
Apr 30, 2026	CONTEXTOR was accepted by ICML 2026.
Apr 16, 2026	I accepted the Ph.D. offer from the Department of Computational Biology at MBZUAI.

Some publications

BinaryAD: Efficient Image Anomaly Detection via Binarized Representations

Junjie Chen, Wenjing Zhang, Pengfei Wang, Bingyang Guo, Hanzhe Liang, Linlin Shen, Jinbao Wang, and Zhichao Lu

Journal Paper of Pattern Recognition, 2026
A Unified Reconstruction Method with Multi-scale Feature Fusion for Multi-category 3D Anomaly Detection

Hanzhe Liang, Chenxi Hu, Yejin Tang, Linlin Shen, Jinbao Wang, and Can Gao

Journal Paper of Neural Networks, 2026
A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Features

Hanzhe Liang, Jie Zhou, Can Gao, Bingyang Guo, Jinbao Wang, and Linlin Shen

Journal Paper of Pattern Recognition, 2025
CONTEXTOR: Contextualized High-order Contrastive Learning

Ze Cai^*, Hanzhe Liang^*, Sihang Zeng, Binbin Zhou^†, and Jun Wen^†

Poster at the Forty-Third International Conference on Machine Learning, 2026
Taming Anomalies with Down-up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection

Hanzhe Liang, Jie Zhang, Tao Dai, Linlin Shen, Jinbao Wang, and Can Gao

Oral presentation at the 33rd ACM International Conference on Multimedia, 2025
Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection

Hanzhe Liang, Guoyang Xie, Chengbin Hou, Bingshu Wang, Can Gao^†, and Jinbao Wang^†

Poster at the AAAI Conference on Artificial Intelligence, 2025

Some working papers

3D Anomaly Detection: A Survey

Hanzhe Liang^*, Bingyang Guo^*, Yawen Huang^*, Jiayi Lyu, Can Gao^†, Yunkang Cao, Jinbao Wang^†, Ruiyun Yu, Llinlin Shen, and Pan Li

ArXiv Preprint, 2026
Open-Set Supervised 3D Anomaly Detection: An Industrial Dataset and a Generalisable Framework for Unknown Defects

Hanzhe Liang^*, Luocheng Zhang^*, Junyang Xia, HanLiang Zhou, Bingyang Guo, Yingxi Xie, Can Gao, Ruiyun Yu, Jinbao Wang, and Pan Li

arXiv preprint arXiv:2604.01171, 2026
IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detection

Bingyang Guo, Hongjie Li, Ruiyun Yu, Hanzhe Liang, and Jinbao Wang

arXiv preprint arXiv:2511.03267, 2025
C3D-AD: Toward Continual 3D Anomaly Detection via Kernel Attention with Learnable Advisor

Haoquan Lu, Hanzhe Liang, Jie Zhang, Chenxi Hu, Jinbao Wang, and Can Gao

arXiv preprint arXiv:2508.01311, 2025