Haozheng Wan

Haozheng Wan

PHD student at HKU, B.Eng. at HIT

Haozheng(Hadrian) Wan - 万浩正

Ph.D. Candidate

Department of Electrical and Computer Engineering, CANLab
The University of Hong Kong

I explore the intersection of efficient AI, privacy-preserving computation, agent governance, and hardware-aware design for intelligent systems under real-world computing and security constraints.

About me

I am a third-year Ph.D. student in the Department of Electrical and Computer Engineering at The University of Hong Kong, supervised by Prof. Can Li at the Cognitive and Adaptive Neuromorphic Computing Lab (CANLab). Currently, I’m working on hardware-algorithm co-design for next-generation AI computing systems, particularly leveraging analog computing-in-memory (CIM) and device-level stochasticity in emerging memories.

My work spans from harnessing intrinsic analog errors for hardware security and computational provenance, to regulating these errors for privacy-preserving computation, and toward monolithic 3D (M3D) architectures that not only transcend analog variability but also support more diverse operators and larger on-chip bandwidth for fully homomorphic encryption.

Prior to Hong Kong, I received my B.S. degree from the Department of Microelectronics Science and Engineering, Harbin Institute of Technology (HIT) in 2023, where I graduated ranked 1st in my cohort. During my undergraduate studies, I was also fortunate to participate in exchange programs at Peking University and the University of Macau, working on AI computing systems and analog IC design. You can find more details about my research and ongoing work on my Projects page. If you are interested in my research and looking for academic discussion, feel free to reach out to me through email.

Research Directions

My research is centered on Making Intelligence Governable: building intelligent systems that are efficient, private, reliable, traceable, and controllable across algorithms, agents, and computing hardware.

AI and agent governance Studying methods that make intelligent models and agents reliable, traceable, and controllable during generation, reasoning, and tool use.
Privacy-preserving intelligent computation Protecting data, models, and computation through cryptographic and system-level mechanisms for AI workloads.
Hardware-aware efficient AI Co-designing algorithms, circuits, and architectures so intelligent workloads run efficiently across emerging computing platforms.
Emerging computing substrates Exploring analog CIM, device stochasticity, and monolithic 3D architectures as physical foundations for governable AI computing.

News

  • Candidature confirmed! I am now a Ph.D. candidate.
  • I joined The University of Hong Kong as a Ph.D. student.
  • I obtained my B.Eng. degree in Microelectronics from HIT.
  • I built my own homepage.

Contact

Academic discussion and research questions are welcome by email.