Yuankun Xia

Yuankun Xia

Ph.D. student

© 2026

About Me

I am a Ph.D. student in Prof. Hui Wang’s research group at Zhejiang Normal University, Jinhua, China.

My research focuses on federated learning and edge intelligence, particularly communication-efficient learning, knowledge distillation, and generalization across domains. I am also interested in wireless communications and parameter-efficient fine-tuning with LoRA.

Email: yuankunx@zjnu.edu.cn · GitHub: Yuankun-Xia

News · Publications · Education · Academic Service


News

  • 2026.07 — Our paper on communication-efficient federated domain generalization was accepted at IEEE GLOBECOM 2026.
  • 2026.05 — I passed the interview and received an offer for the integrated master’s–Ph.D. program.
  • 2026.01 — FedCLIP-Distill was accepted by Knowledge-Based Systems.
  • 2025.09 — pFedMLKD was accepted by IEEE Internet of Things Journal.

Publications

Journal Papers

First-Author Papers

  • FedCLIP-Distill: Heterogeneous federated cross-modal knowledge distillation for multi-domain visual recognition
    Yuankun Xia, Hui Wang*, and Yufeng Zhou.
    Knowledge-Based Systems (KBS), 2026. · Paper

  • pFedMLKD: A Novel Framework for Personalized Federated Learning via Multilevel Distillation
    Yuankun Xia, Hui Wang*, Di Yin, Yiteng Zhang, and Qian Huang.
    IEEE Internet of Things Journal (IoTJ), 2025. · Paper

Other Co-authored Papers

  • In-loop kernel refinement: Robust blind inverse problems via conditional diffusion and sparse Bayesian learning
    Ziyu Hong, Yuankun Xia, and Hui Wang*.
    Neurocomputing, 2026. · Paper

  • LBCM: A Scalable and DDoS-resistant Cross-domain Authentication Protocol for IIoT using Chaotic Maps and Merkle Tree
    Yu Huang, Maode Ma, Hui Wang*, Yuankun Xia, and Yinjuan Shi.
    IEEE Internet of Things Journal (IoTJ), 2026. · Paper

  • MMC-CS: Multi-branch multi-stage contrastive learning for self-supervised compressed sensing
    Yiteng Zhang, Hui Wang*, and Yuankun Xia.
    Neural Networks (NN), 2026. · Paper

Conference Papers

First-Author Papers

  • Communication-Efficient Federated Domain Generalization in Edge Networks via Dynamic Prototype Regulation
    Yuankun Xia, Hui Wang*, Ling Yuan, Ziyu Hong, Di Yin, and Yufeng Zhou.
    IEEE Global Communications Conference (GLOBECOM), 2026. · Preprint

Other Co-authored Papers

  • MPDU: Momentum-Preserving Diffusion Unrolling via Explicit Subspace Decoupling for Compressed Sensing
    Yufeng Zhou, Yiteng Zhang, Yuankun Xia, and Hui Wang*.
    IEEE International Conference on Multimedia & Expo (ICME), 2026.

  • A Lightweight Blockchain-Based Cross-Domain Authentication and Key Agreement Protocol for Industrial IoT
    Yu Huang, Maode Ma, Hui Wang*, Na Li, and Yuankun Xia.
    IEEE International Conference on Communications (ICC), 2026. · Paper


Education

  • Zhejiang Normal University · 2024–2030 (expected)
    Ph.D. in Computer Science and Technology.
  • Huaibei Normal University · 2020–2024
    Bachelor’s degree in Intelligence Science and Technology.

Academic Service

Peer Review

  • AAAI Conference on Artificial Intelligence (AAAI).
  • IEEE Transactions on Mobile Computing (TMC).
  • IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP).
  • npj Digital Medicine.
  • The Web Conference (WWW).