DENOS Lab, University of Calgary ← Back to team
Jiajun Wu

Jiajun Wu

PhD Candidate in Electrical and Software Engineering, University of Calgary

Large Language Model Application, Federated Learning

Google Scholar

Biography

Jiajun Wu is a PhD candidate at DENOS Lab working on federated learning and large language model applications. His survey Topology-aware Federated Learning in Edge Computing is published in ACM Computing Surveys and was selected for the ACM Showcase, and his work now extends to clinical decision support, where he leads the lab’s patient chart summarization and small language model benchmarking for emergency departments.

Projects

  • EDSim

    Large language model simulation of an emergency department with autonomous agents for patients, nurses, and physicians.

  • Patient chart summarization

    Dual-stage summarization that runs offline on embedded devices so emergency physicians get structured findings without patient data leaving the device.

Publications

  • ACM CSUR2024

    Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey

    Jiajun Wu, Fan Dong, Henry Leung, Zhuangdi Zhu, Jiayu Zhou, and Steve Drew

    paper

  • IEEE ICC2023

    FedLE: Federated Learning Client Selection with Lifespan Extension for Edge IoT Networks

    Jiajun Wu, Steve Drew, and Jiayu Zhou

    paper

  • IEEE AIoT2025

    Dual-stage and Lightweight Patient Chart Summarization for Emergency Physicians

    Jiajun Wu, Swaleh Zaidi, et al.

    paper

  • IEEE ATC2025

    Small Language Models for Emergency Departments Decision Support: A Benchmark Study

    Jiajun Wu, et al.

  • arXiv2025

    A Survey on Task Scheduling in Carbon-aware Container Orchestration

    Jialin Yang, Zainab Saad, Jiajun Wu, Xiaoguang Niu, Henry Leung, and Steve Drew

    paper

  • AAAI/ACM AIES2024

    Enhancing Equitable Access to AI in Housing and Homelessness System of Care through Federated Learning

    Musa Taib, Jiajun Wu, Steve Drew, and Geoffrey Messier

  • CJEM2026

    Can human-aware agentic artificial intelligence transform emergency care workflows?

    Jiajun Wu, et al.

Achievements

  • Topology-aware Federated Learning in Edge Computing selected for the ACM Showcase.
  • Third place in data visualization at the CANIS Hackathon hosted by Schulich Ignite, with Leo Wei and Yunkai Bao.

← All team members