I am a Ph.D. Candidate in Electrical Engineering at the City University of Hong Kong, specializing in machine learning, computer vision, and data mining. My research explores scalable algorithms for pattern recognition, clustering, and computational intelligence, with applications in real-world measurement systems, blockchain technology, and biomedical image analysis.
- Machine Learning
- Computer Vision
- Natural Language Processing
- Data Mining
- Financial Engineering
- LMEraser: Large model unlearning via adaptive prompt tuning – 28th International Conference on Artificial Intelligence and Statistics (AISTATS), 2025. (Equal contribution first author)
- Scalable co-clustering for large-scale data through dynamic partitioning and hierarchical merging – IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2024.
- Ellipse detection via global arc compatibilities and adaptive co-clustering for real-world measurement systems – IEEE Transactions on Instrumentation & Measurement, 2024.
- A convex-hull based method with manifold projections for detecting cell protrusions – Computers in Biology and Medicine, 2024. (Equal contribution first author)
- X-Shard: Optimistic cross-shard transaction processing for sharding-based blockchains – IEEE Transactions on Parallel and Distributed Systems, 2024.
- Machine unlearning: Solutions and challenges – IEEE Transactions on Emerging Topics in Computational Intelligence, 2024.
- Physical Activity Assessment System And Method – HK30081186, May 2023.
I have served as a teaching assistant for the following courses at City University of Hong Kong:
- Topics in Computer Graphics (EE5808) – Spring 2024, Spring 2023
- Design Project (EE3070) – Fall 2023, Fall 2022
- Linear Systems Theory & Design (EE6620) – Fall 2021
- Programming: C++, MATLAB, PyTorch
- Languages: TOEFL: 107/120 (Speaking: 23)
- Email: [email protected] | [email protected]
- Phone: (+852) 9810 6427 | (+86) 188 5695 6416
- LinkedIn: Zihan Wu
This repository serves as a collection of my research projects, code implementations, and other related academic work. Contributions, feedback, and collaborations are welcome!