Hailiang ZHAO

Biography

I am a ZJU 100 Young Professor (平台“百人计划”研究员) in the School of Software Technology, Zhejiang University (ZJU). I obtained my PhD from the College of Computer Science and Technology at ZJU in June 2024, supervised by Prof. Shuiguang Deng. From September 2022 to September 2023, I was a visiting PhD student at the PDCL Lab, Nanyang Technological University (NTU), under the supervision of Prof. Xueyan Tang.

面向 2026 年 9 月入学的硕士生，本人额外还有 2 个名额，对我课题组感兴趣的同学，欢迎邮件联系。

[Google Scholar] [ResearchGate] [ZJU Homepage] [CV]

Research Interests (Selected)

• Learning-Augmented Algorithms & Systems (2023 - present). I investigate how to integrate machine learning predictions into classical algorithmic frameworks to improve decision-making under uncertainty and non-stationarity. My work emphasizes practical robustness, theoretical guarantees, and system-aware deployment. Representative outcomes include PFSUM (NeurIPS '24) for the Bahncard problem and Guard (NeurIPS '25), a robustification framework for online caching that achieves consistency without sacrificing competitiveness (AcademicDaily 推文). I also led Learning-Augmented Systems, which proposes a general architecture for embedding predictive models into system control loops, enabling adaptive autoscaling, request routing, and resource provisioning in MLSys and microservices platforms. A concrete instantiation of our work is LCR, which delivers performance gains while ensuring robustness and efficiency on ML-based GPU caching for modern inference.

• Multimodal Data Intelligence (2025 - present). I develop adaptive, semantics-aware methods for fusing and reasoning over heterogeneous, time-varying data modalities, i.e., sensor streams, vision, language, and operational logs, to support complex downstream tasks in dynamic real-world environments. My approach jointly addresses temporal misalignment, modality imbalance, and distribution shifts, with an emphasis on interpretability, generalization, and input reliability. This line of work includes CADRef (CVPR '25), a class-aware out-of-distribution detector that enhances multimodal pipeline robustness by monitoring data quality, as well as applications in vehicular 3D grounding (TrackTeller), industrial predictive maintenance (OmniFuser), water quality forecasting (XFMNet), and microservice tail latency prediction via unified system representations (USRFNet). Across these efforts, I aim to build lightweight yet expressive pipelines that turn uncertain multimodal inputs into reliable, actionable insights.

• Resource Scheduling in Emerging Computing Paradigms (2019 - present). I study resource allocation, job scheduling, and service orchestration in distributed systems characterized by heterogeneity, mobility, and latency sensitivity, particularly in edge computing and cloud-edge continuum architectures. My early work established algorithms for distributed multi-server scheduling with theoretical performance analysis (TAOS, TSC '25; OnSocMax, TSC '25; OGASched, TSC '23; ESDP, TPDS '22; DPE, TPDS '21), decentralized network slicing (DPoS, TMC '22), and mobility-aware offloading (CCO, ICWS '19, Best Student Paper). I also developed PeerSync (TSC '25), an edge-optimized container image distribution system that outperforms Alibaba's Dragonfly and Uber's Kraken in bandwidth-constrained edge environments through peer-assisted delivery and topology-aware coordination.

If you are interested in my research and would like to pursue a Master's or Ph.D. under my supervision, please feel free to send an email to: hliangzhao {AT} zju {DOT} edu {DOT} cn.

Selected Papers

• Jiaji Zhang, Hailiang Zhao^*, Guoxuan Zhu, Ruichao Sun, Jiaju Wu, Xinkui Zhao, Hanlin Tang, Weiyi Lu, Kan Liu, Tao Lan, Lin Qu, and Shuiguang Deng^*, Shiva-DiT: Residual-Based Differentiable Top-k Selection for Efficient Diffusion Transformers. In: arXiv preprints.

• Zhiwei Ling, Hailiang Zhao^*, Chao Zhang, Xiang Ao, Ziqi Wang, Cheng Zhang, Zhen Qin, Xinkui Zhao, Kingsum Chow^*, Yuanqing Wu, and MengChu Zhou, Adaptive Dual-Weighting Framework for Federated Learning via Out-of-Distribution Detection. In: arXiv preprints.

• Yu Tang^†, Hailiang Zhao^†*, Chuansheng Lu, Yifei Zhang, Kingsum Chow^*, and Shuiguang Deng, and Rui Shi, Morphis: SLO-Aware Resource Scheduling for Microservices with Time-Varying Call Graphs. In: arXiv preprints.

• Hailiang Zhao, Ziqi Wang, Daojiang Hu, Zhiwei Ling, Wenzhuo Qian, Jiahui Zhai, Yuhao Yang, Zhipeng Gao, Mingyi Liu, Kai Di, Xinkui Zhao, Zhongjie Wang, Jianwei Yin, MengChu Zhou, and Shuiguang Deng, Industrial Data-Service-Knowledge Governance: Toward Integrated and Trusted Intelligence for Industry 5.0. In: arXiv preprints.

• Jiahong Yu^†, Ziqi Wang^†, Hailiang Zhao^*, Wei Zhai, Xueqiang Yan, and Shuiguang Deng, TrackTeller: Temporal Multimodal 3D Grounding for Behavior-Dependent Object References. In: arXiv preprints.

• Ziqi Wang, Hailiang Zhao^*, Yuhao Yang, Daojiang Hu, Cheng Bao, Mingyi Liu, Kai Di, Schahram Dustdar, Zhongjie Wang, and Shuiguang Deng, OmniFuser: Adaptive Multimodal Fusion for Service-Oriented Predictive Maintenance. In: arXiv preprints.

• Shuiguang Deng^*, Hailiang Zhao^*, Ziqi Wang, Guanjie Cheng, Peng Chen, Wenzhuo Qian, Zhiwei Ling, Jianwei Yin, Albert Y. Zomaya, and Schahram Dustdar, Agentic Services Computing. In: arXiv preprints.

• Peng Chen, Jiaji Zhang, Hailiang Zhao^*, Yirong Zhang, Jiahong Yu, Xueyan Tang, Yixuan Wang, Hao Li, Jianping Zou, Gang Xiong, Kingsum Chow, Shuibing He, Shuiguang Deng^*, Toward Robust and Efficient ML-Based GPU Caching for Modern Inference. In: arXiv preprints.

• Ziqi Wang, Hailiang Zhao^*, Cheng Bao, Wenzhuo Qian, Yuhao Yang, Xueqiang Sun, and Shuiguang Deng^*, XFMNet: Decoding Cross-Site and Nonstationary Water Patterns via Stepwise Multimodal Fusion for Long-Term Water Quality Forecasting. In: arXiv preprints.

• Wenzhuo Qian, Hailiang Zhao^*, Tianlv Chen, Jiayi Chen, Ziqi Wang, Kingsum Chow, and Shuiguang Deng^*, Learning Unified System Representations for Microservice Tail Latency Prediction. In: arXiv preprints.

• Jiaji Zhang, Ruichao Sun, Hailiang Zhao^*, Jiaju Wu, Peng Chen, Hao Li, Yuying Liu, Kingsum Chow, Gang Xiong, and Shuiguang Deng^*, SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models. To be proceeded in the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR '26). (AcademicDaily 推文)

• Yinuo Deng^†, Hailiang Zhao^†*, Dongjing Wang, Peng Chen, Wenzhuo Qian, Jianwei Yin, Schahram Dustdar, and Shuiguang Deng^*, PeerSync: Accelerating Containerized Model Inference at the Network Edge. In: IEEE Transactions on Services Computing (TSC), early access, doi: 10.1109/TSC.2025.3648591.

• Peng Chen, Hailiang Zhao^*, Jiaji Zhang, Xueyan Tang, Yixuan Wang, and Shuiguang Deng^*, Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency. In: Proceedings of the 39th Conference on Neural Information Processing Systems (NeurIPS '25).

• Hailiang Zhao, Xueyan Tang^*, Peng Chen, Jianwei Yin, and Shuiguang Deng, Data-Locality-Aware Task Assignment and Scheduling for Distributed Job Executions. In: IEEE Transactions on Services Computing (TSC), early access, doi: 10.1109/TSC.2025.3594158. [Code]

• Hailiang Zhao, Ziqi Wang, Guanjie Cheng^*, Wenzhuo Qian, Peng Chen, Jianwei Yin, Schahram Dustdar, and Shuiguang Deng^*, Online Workload Scheduling for Social Welfare Maximization in the Computing Continuum. In: IEEE Transactions on Services Computing (TSC), early access, doi: 10.1109/TSC.2025.3570845.

• Fan'an Meng, Hongjun Dai^*, Guoqing Cong, Bo Zhu, and Hailiang Zhao, CATScaler: A Convolution-Augmented Transformer Scaling Framework for Cloud-Native Applications. In: IEEE Transactions on Services Computing (TSC), early access, doi: 10.1109/TSC.2025.3592383.

• Cheng Zhang, Yinuo Deng, Hailiang Zhao^*, Tianlv Chen, and Shuiguang Deng^*, Tail-Learning: Adaptive Learning Method for Mitigating Tail Latency in Autonomous Edge Systems. In: ACM Transactions on Autonomous and Adaptive Systems (TAAS), early access, doi: https://doi.org/10.1145/3737289.

• Zhiwei Ling, Yachen Chang, Hailiang Zhao^*, Xinkui Zhao, Kingsum Chow^*, and Shuiguang Deng, CADRef: Robust Out-of-Distribution Detection via Class-Aware Decoupled Relative Feature Leveraging. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025 (CVPR '25). [Code] [Poster]

• Hailiang Zhao, Xueyan Tang, Peng Chen, and Shuiguang Deng, Learning-Augmented Algorithms for the Bahncard Problem. In: Proceedings of the 38th Conference on Neural Information Processing Systems (NeurIPS '24). [Code] [Slide] [Poster]

• Shuiguang Deng^*, Hailiang Zhao^*, Bingbing Huang, Cheng Zhang, Feiyi Chen, Yinuo Deng, Jianwei Yin, Schahram Dustdar, and Albert Y. Zomaya, Cloud-Native Computing: A Survey from the Perspective of Services. In: Proceedings of the IEEE (JPROC), vol. 112, no. 1, pp. 12-46, Jan. 2024, doi: 10.1109/JPROC.2024.3353855. (Cover Paper, 2024-2025 IF = 25.9)

• Hailiang Zhao, Shuiguang Deng^*, Zhengzhe Xiang, Xueqiang Yan, Jianwei Yin, Schahram Dustdar, and Albert Y Zomaya, Scheduling Multi-Server Jobs with Sublinear Regrets via Online Learning. In: IEEE Transactions on Services Computing (TSC), vol. 17, no. 3, pp. 1168-1180, May-June 2024, doi: 10.1109/TSC.2023.3303344.

• Hailiang Zhao, Shuiguang Deng^*, Feiyi Chen, Jianwei Yin, Schahram Dustdar, and Albert Y. Zomaya, Learning to Schedule Multi-Server Jobs with Fluctuated Processing Speeds. In: IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 34, no. 1, pp. 234-245, 1 Jan. 2023, doi: 10.1109/TPDS.2022.3215947. [Slide]

• Shuiguang Deng, Hailiang Zhao, Zhengzhe Xiang, Cheng Zhang, Rong Jiang, Ying Li^*, Jianwei Yin, Schahram Dustdar, and Albert Y. Zomaya, Dependent Function Embedding for Distributed Serverless Edge Computing. In: IEEE Transactions on Parallel and Distributed Systems (TPDS), vol. 33, no. 10, pp. 2346-2357, October 2022, doi: 10.1109/TPDS.2021.3137380.

• Hailiang Zhao, Shuiguang Deng^*, Zijie Liu, Zhengzhe Xiang, Jianwei Yin, Schahram Dustdar, and Albert Y. Zomaya, DPoS: Decentralized, Privacy-Preserving, and Low-Complexity Online Slicing for Multi-Tenant Networks. In: IEEE Transactions on Mobile Computing (TMC), vol. 21, no. 12, pp. 4296-4309, 1 Dec. 2022, doi: 10.1109/TMC.2021.3074934. (2021 Trending Paper) [Slide]

• Hailiang Zhao, Shuiguang Deng^*, Zijie Liu, Jianwei Yin, and Schahram Dustdar, Distributed Redundant Placement for Microservice-based Applications at the Edge. In: IEEE Transactions on Services Computing (TSC), vol. 15, no. 3, pp. 1732-1745, 1 May-June 2022, doi: 10.1109/TSC.2020.3013600. [Slide] (ESI Highly Cited Paper)

• Shuiguang Deng, Hailiang Zhao, Weijia Fang^*, Jianwei Yin, Schahram Dustdar, and Albert Y. Zomaya, Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence. In: IEEE Internet of Things Journal (IoTJ), vol. 7, no. 8, pp. 7457-7469, Aug. 2020, doi: 10.1109/JIOT.2020.2984887. (Sep 2020 Popular Paper, ESI Hot Paper, ESI Highly Cited Paper, 21k+ full text read on IEEE Explore, Ranked No. 1 in paper readership at ZJU on ResearchGate in 2020)

• Hailiang Zhao, Shuiguang Deng^*, Cheng Zhang, Wei Du, Qiang He, and Jianwei Yin, A Mobility-aware Cross-edge Computation Offloading Framework for Partitionable Applications. In: Proceedings of the 17th IEEE International Conference on Web Services (ICWS '19), Milan, Italy, 2019. [Slide] [Theoretical Analysis] (Best Student Paper)

Selected Projects

• 全要素互联结构自适应的多模态数据治理技术体系，国家重点研发计划课题，主持 (2024-2027)
• 基于软硬件协同的服务调度与资源管理优化方法研究，国家自然科学基金青年科学基金项目（C类），主持 (2026-2028)
• 面向生成式 AI 的异构硬件资源优化与计算加速理论与方法，浙江省科技厅自然科学基金重大项目，参与 (2025-2027)
• 快手推理场景下典型 GPU 服务的吞吐量提高，快手技术合作项目，共同主持 (2024-2025)
• 面向异构集群的微服务性能分析与资源调度，字节跳动技术合作项目，参与 (2025-2026)

Selected Awards & Honors

• 2024 年浙江省优秀博士学位论文提名 (2026)
• 2025 SICI 最佳论文奖 (2025)
• 数据要素赋能新型工业化大赛决赛二等奖 (2025)
• CCF 中国服务计算创新大赛暨深信服杯算法竞赛决赛二等奖（指导学生获奖） (2025)
• CCF 服务计算专委博士学位论文激励计划 (2025)
• 浙江大学启真优秀青年学者 (2024)
• 浙江大学优秀博士学位论文 (2024)
• 浙江大学博新奖学金 (2019)
• 2019 IEEE ICWS 最佳学生论文奖 (2019)
• 武汉理工大学卓越奖学金 (校最高学生奖励) (2018)

Professional Services

I am serving as chair, program chair member and reviewer for several conferences/workshops/forums and journals.

• 计算机工程与科学, 青年编委; Electronics, guest editor
• IJCAI-ECAI '26, PAKDD '26, AAAI '26, IJCAI '25, ECAI '25, etc., PC member & reviewer; ICML '26, ECCV '26, CVPR '26, NeurIPS '25, CVPR '25, etc., reviewer
• TMC, TSC, 计算机学报, FGCS, TKDD, Scientific Reports, TGCN, IoTJ, MONET, etc., reviewer

Some Research Materials & Resources

• Understanding Acceleration Opportunities for Microservice Overheads at Hyperscale (Jun 2024)
• Characterizing Microservice Dependency and Performance: Alibaba Trace Analysis (May 2024)
• Online Interval Scheduling (Mar 2024)
• Transformation Techniques in Optimization (Feb 2024)
• Everything about ADMM (Nov 2022)
• Distributed Systems in One Slide (Oct 2022)
• ADMM: The Variational Inequality Perspective (Oct 2022)
• An Overview of Kubernetes Scheduling (Oct 2022)
• 优化算法复杂度分析 (Oct 2022)
• 最优化理论基础 (Jul 2021)
• Park: An Open Platform for Learning-Augmented Computer Systems (Jan 2021)
• 理解共轭梯度法 (Jul 2020)
• 需要熟练掌握的算法理论基础 (May 2020)
• How Should I Slice My Network? (Dec 2019)
• 李雅普诺夫优化导论 (Nov 2018)

Correspondence

Emails: hliangzhao {AT} ZJU {DOT} edu {DOT} cn, hliangzhao97 {AT} gmail {DOT} com

Address:

• Room 3#403, Ningbo Campus of Zhejiang University (浙江省宁波市鄞州区学府路 5 号, 浙江大学宁波国际科创中心 (宁波校区) 315100)
• Room 422, Cao Guangbiao Sci-tech Building, Yuquan Campus of Zhejiang University (中国浙江省杭州市西湖区浙大路 38 号，浙江大学玉泉校区 310027)