Xuchuang Wang
Assistant Professor, Department of Computer Science, HKBU
I am an Assistant Professor in the Department of Computer Science at Hong Kong Baptist University. My research develops the algorithmic foundations of quantum information and computing, with a focus on quantum networking, quantum machine learning, and an expanding direction in distributed quantum computing.
I study how quantum resources can be used efficiently for communication, learning, and computation:
- Quantum networking: how to distribute entanglement, select reliable paths, and characterize noisy quantum links.
- Quantum machine learning: when quantum access to information can accelerate learning and sequential decision-making.
- Distributed quantum computing: how to coordinate entanglement, communication, and computation across interconnected quantum processors.
My approach combines learning theory, quantum algorithms, and optimization. Online learning, bandits, and reinforcement learning provide tools for making decisions under uncertainty; quantum information brings new opportunities and constraints. I aim to develop algorithms with provable guarantees that account for noise, limited measurements, and scarce quantum resources.
research highlights and directions
Quantum networking
I develop learning algorithms for the quantum internet, including entanglement routing, link selection, and network tomography. The central challenge is to make reliable decisions when link quality is uncertain and measurements consume valuable quantum resources.
- Network characterization: quantum-classical coexistence tomography (QCE’26, Best Paper Award), adaptive probe allocation (QCNC’26), and network evaluation (Mergecast preprint).
- Routing and resource allocation: learning entanglement paths (INFOCOM’25) and selecting quantum links with fidelity estimation (INFOCOM’24).
Quantum machine learning
I study quantum advantages in learning and sequential decision-making, especially quantum bandits and best-arm identification. My work examines both the speedups enabled by quantum access and the constraints that affect whether those speedups can be realized.
- Quantum learning algorithms: best-arm and top-arm identification with quantum oracles (AAAI’25, QCE’25).
- Resource constraints: quantum learning with limited rounds of adaptivity (NeurIPS’26a) and quantum bandits under memory decoherence (NeurIPS’26b).
Learning theory and broader applications
My broader work develops foundations for learning with limited, heterogeneous, or unreliable feedback. Topics include communication-efficient cooperative learning (SIGMETRICS’25, NeurIPS’25), robustness to manipulated feedback (ICLR’25), and learning from multiple feedback sources (ICML’25, NeurIPS’23). Related applications include agentic networking and LLM evaluation and alignment (AAAI’26).
See my publications for the full list of papers and my quantum networking overview for an introduction to that area.
joining the lab
I welcome students and researchers interested in the mathematical and algorithmic questions behind quantum networks, quantum learning, and distributed quantum computation. Strong foundations in probability, optimization, or theoretical computer science are especially useful. Applicants from computer science, mathematics, and physics are all welcome.
Alongside Ph.D. and postdoctoral positions, I host Research Assistants on 3- or 6-month terms, remotely or onsite at HKBU. These positions suit senior undergraduates, master’s students, and recent graduates who want to explore research, prepare for a Ph.D., or develop a project toward publication.
Students in my group publish at venues including NeurIPS, ICML, ICLR, AAAI, SIGMETRICS, and INFOCOM, and collaborate with researchers at UMass, CUHK, CityU, NJU, and SJTU. Meet recent mentees and see their work on the team page. For available positions, research topics, and application instructions, visit openings.
background
Before joining HKBU, I was an RGC Junior Research Fellow in the Department of Computer Science and Engineering at The Chinese University of Hong Kong. Previously, I spent three years as a postdoctoral researcher at UMass Amherst, working with Don Towsley in ACQUIRE Lab and Mohammad Hajiesmaili in SOLAR Lab.
I received my Ph.D. in Computer Science and Engineering from CUHK, advised by John C.S. Lui in ANSR Lab, and my B.Eng. with Honours from Xi’an Jiaotong University through the honours program now known as Qian Xuesen Honors College.
My work has received the Best Paper Award at IEEE Quantum Week (QCE) 2026 and the Best Paper Runner-Up at ACM SIGMETRICS 2025.
news
| Oct 27, 2026 | Invited to give a talk on quantum bandits at Fudan University (online). |
|---|---|
| Sep 30, 2026 | Five papers are accepted by NeurIPS 2026. One scales quantum bandits to over 1000 arms on IBM quantum hardware by tackling memory decoherence. The other attains the quantum speedup with only log*(n)+1 rounds of adaptivity. The other three cover multi-agent learning in matching markets, adversarial attacks on bandits, and fused reward and dueling feedback. Many thanks to all my collaborators! |
| Aug 28, 2026 | Our paper Quantum-Classical Coexistence Network Tomography received the Best Paper Award at IEEE Quantum Week (QCE) 2026. |
| Aug 11, 2026 | Our paper Efficient Quantum Link Selection and Fidelity Estimation Under Success Rate Constraints is accepted by IEEE Transactions on Networking. |
| Aug 07, 2026 | Invited as a TPC for INFOCOM 2027!  |