Ziyang Zhang

prof_pic.jpg

I am currently a Postdoctoral Researcher in the NESLab at Politecnico di Milano, working with Prof. Luca Mottola. I obtained my Ph.D. degree from Harbin Institute of Technology in 2024, advised by Prof. Jie Liu (IEEE Fellow, ACM Distinguished Scientist).

My main research interest is edge computing, embedded intelligence, with a focus on high-performance and energy-efficent edge DNN inference.

  • DNN Compilation Optimization (POS, TOP)
  • Task Scheduling and Resource Allocation (Octopus, BCEdge, ECSRL)
  • Collaborative AI (DVFO)
  • Energy-efficient DNN inference (E4, E3)

You can access my resume here.

Recent News

Jan 22, 2025 One paper was accepted by ACM SenSys 2025! (Acceptance Rate: 46/245, 18.8%)
Dec 10, 2024 One paper was accepted by AAAI 2025!
Dec 03, 2024 One paper was accepted by IEEE Trans. on Parallel and Distributed Systems 2024!
Jun 05, 2024 One paper was accepted by IEEE Trans. on Network and Service Management 2024!
Jan 23, 2024 One paper was accepted by IEEE Trans. on Mobile Computing 2024!
Sep 20, 2023 One paper was accepted by ICSOC 2023! (Acceptance Rate: 35/208, 16.8%)
May 09, 2023 One paper was accepted by IPSN 2023! (Acceptance Rate: 22/83, 26.5%)

Selected Publications

  1. SenSys’25
    E3: Early Exiting with Explainable AI for Real-Time and Accurate DNN Inference in Edge-Cloud Systems
    Changyao Lin, Zhenming Chen, Ziyang Zhang, and 1 more author
    In SenSys, 2025
  2. AAAI’25
    E4: Energy-Efficient Early-Exit DNN Inference Framework for Edge Video Analytics
    Ziyang Zhang, Yang Zhao, Chang Ming-Ching, and 2 more authors
    In AAAI, 2025
  3. IEEE TPDS’24
    TOP: Task-Based Operator Parallelism for Asynchronous Deep Learning Inference on GPU
    Changyao Lin, Zhenming Chen, Ziyang Zhang, and 1 more author
    IEEE Transactions on Parallel and Distributed Systems, 2024
  4. IEEE TMC’24
    DVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference
    Ziyang Zhang, Yang Zhao, Huan Li, and 2 more authors
    IEEE Transactions on Mobile Computing, 2024
  5. ICSOC’23
    Octopus: SLO-Aware Progressive Inference Serving via Deep Reinforcement Learning in Multi-tenant Edge Cluster
    Ziyang Zhang, Yang Zhao, and Jie Liu
    In International Conference on Service-Oriented Computing, 2023
  6. IPSN’23
    Pos: An operator scheduling framework for multi-model inference on edge intelligent computing
    Ziyang Zhang, Huan Li, Yang Zhao, and 2 more authors
    In Proceedings of the 22nd International Conference on Information Processing in Sensor Networks, 2023