Publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

† denotes equal contribution.

2026

  1. EuroMLSys
    Harnessing Idle Compute at the Edge for Foundation Model Training
    Leyang Xue, Meghana Madhyastha, Myungjin Lee, Amos Storkey, Randal Burns, and Mahesh Marina
    In EuroMLSys, co-located with EuroSys, 2026
  2. HotMobile
    Towards Automated RAN Configuration Tuning in Cellular Networks with Causal Learning
    Leyang Xue, Bolun Zhang, Mahesh Marina , He Yan, Yu Zhou, Cheuk Yiu Ip, and James Klosowski
    In HotMobile, 2026
  3. SIGCOMM
    CausalTune: Causal Learning based Automated Cellular RAN Configuration Tuning Framework
    Leyang Xue†, Bolun Zhang†, Yibo Ma, Mahesh Marina , He Yan, Yu Zhou, Cheuk Yiu Ip, Senthil Dhandapani, and 1 more author
    In SIGCOMM, 2026
  4. OSDI
    BatchGen: An Architecture for Scalable and Efficient Batch Inference
    Tairan Xu†, Leyang Xue†, Zhan Lu†, Jinfu Deng, Hongyang Xiao, Yinsicheng Jiang, Congjie He, Matej Sandor, and 2 more authors
    In OSDI, 2026
  5. EdgeSys
    Morphling: Emulator for Distributed Machine Learning at the Edge
    Leyang Xue, Yufeng Xia, Eren Mendi, Ismaeel Bashir, Jiaxun Yang, Myungjin Lee, and Mahesh K. Marina
    In EdgeSys, 2026
    Best Paper Code

2025

  1. HotCarbon
    Towards Decentralized and Sustainable Foundation Model Training with the Edge
    Leyang Xue, Meghana Madhyastha, Randal Burns, Myungjin Lee, and Mahesh K. Marina
    SIGENERGY Energy Inform. Rev., 2025
    arXiv
  2. arXiv
    On Harnessing Idle Compute at the Edge for Foundation Model Training
    Leyang Xue, Meghana Madhyastha, Myungjin Lee, Amos Storkey, Randal Burns, and Mahesh K. Marina
    2025
    arXiv
  3. MobiCom
    Poster: On Harnessing Idle Compute at the Edge for Foundation Model Training
    Leyang Xue, Meghana Madhyastha, Myungjin Lee, Amos Storkey, Randal Burns, and Mahesh Marina
    In MobiCom, 2025
  4. ICDCS
    HybridServe: Efficient Serving of Large AI Models with Confidence-Based Cascade Routing
    Leyang Xue, Yao Fu, Luo Mai, and Mahesh K. Marina
    In The 45th IEEE International Conference on Distributed Computing Systems (ICDCS), 2025
    arXiv
  5. ICDCS
    TUBO: A Tailored ML Framework for Reliable Network Traffic Forecasting
    Zhihang Yuan, Leyang Xue, Waleed Ahsan, and Mahesh K. Marina
    In The 45th IEEE International Conference on Distributed Computing Systems (ICDCS), 2025
  6. arXiv
    MoE-Gen: High-Throughput MoE Inference on a Single GPU with Module-Based Batching
    Tairan Xu, Leyang Xue, Zhan Lu, Adrian Jackson, and Luo Mai
    2025
    arXiv Code
  7. NeurIPS
    MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems
    Yao Fu, Yinsicheng Jiang, Yeqi Huang, Ping Nie, Zhan Lu, Leyang Xue, Congjie He, Man-Kit Sit, and 6 more authors
    In NeurIPS Datasets & Benchmarks Track, 2025
    arXiv Code
  8. NSDI
    Towards Energy Efficient 5G vRAN Servers
    Anuj Kalia, Nikita Lazarev, Leyang Xue, Xenofon Foukas, Bozidar Radunovic, and Francis Y. Yan
    In NSDI, 2025

2024

  1. arXiv
    MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache
    Leyang Xue, Yao Fu, Zhan Lu, Chuanhao Sun, Luo Mai, and Mahesh K. Marina
    2024
    arXiv Code
  2. OSDI
    ServerlessLLM: Low-Latency Serverless Inference for Large Language Models
    Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Luo Mai
    In OSDI, 2024
    Code

2022

  1. ICNP
    PAINT: Path Aware Iterative Network Tomography for Link Metric Inference
    Leyang Xue, Mahesh K. Marina, Geng Li, and Kai Zheng
    In ICNP, 2022