Publications

2026

  1. EuroSys
    Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading
    Hanfei Yu, Xingqi Cui, Hong Zhang, Hao Wang@Rutgers, and Hao Wang
    In ACM European Conference on Computer Systems, 2026
    Link

2025

  1. TPDS
    Accelerating ML Inference via Opportunistic Pre-Loading on Serverless Clusters
    Yifan Sui, Hanfei Yu, Yitao Hu, Jianxun Li, and Hao Wang
    IEEE Transactions on Parallel and Distributed Systems, 2025
    Link
  2. SoCC
    Multi-Agent Reinforcement Learning with Serverless Computing
    Rui Wei, Hanfei Yu, Xikang Song, Jian Li, Devesh Tiwari, Ying Mao, and Hao Wang
    In ACM Symposium on Cloud Computing, 2025
    Link
  3. VLDB
    Nitro: Boosting Distributed Reinforcement Learning with Serverless Computing
    Hanfei Yu, Jacob Carter, Hao Wang, Devesh Tiwari, Jian Li, and Seung-Jong Park
    The VLDB Endowment, 2025
    Link

2024

  1. SoCC
    Pre-Warming is Not Enough: Accelerating Serverless Inference With Opportunistic Pre-Loading
    Yifan Sui, Hanfei Yu, Yitao Hu, Jianxun Li, and Hao Wang
    In ACM Symposium on Cloud Computing, 2024
    Link 🏆 Best Paper Award
  2. TPDS
    Freyr+: Harvesting Idle Resources in Serverless Computing via Deep Reinforcement Learning
    Hanfei Yu, Hao Wang, Jian Li, Xu Yuan, and Seung-Jong Park
    IEEE Transactions on Parallel and Distributed Systems, 2024
    Link
  3. SC
    Stellaris: Staleness-Aware Distributed Reinforcement Learning with Serverless Computing
    Hanfei Yu, Hao Wang, Devesh Tiwari, Jian Li, and Seung-Jong Park
    In ACM/IEEE International Conference for High Performance Computing, Networking, Storage, and Analysis, 2024
    Link 🏆 Best Student Paper Finalist
  4. AAAI
    Cheaper and Faster: Distributed Deep Deinforcement Learning with Serverless Computing
    Hanfei Yu, Jian Li, Yang Hua, Xu Yuan, and Hao Wang
    In The Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024
    Link
  5. ASPLOS
    RainbowCake: Mitigating Cold-starts in Serverless with Layer-wise Container Caching and Sharing
    Hanfei Yu, Rohan Basu Roy, Christian Fontenot, Devesh Tiwari, Jian Li, Hong Zhang, Hao Wang, and Seung-Jong Park
    In ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 1, 2024
    Link

2023

  1. HPDC
    Libra: Harvesting Idle Resources Safely and Timely in Serverless Clusters
    Hanfei Yu, Christian Fontenot, Hao Wang, Jian Li, Xu Yuan, and Seung-Jong Park
    In ACM International Symposium on High-Performance Parallel and Distributed Computing, 2023
    Link

2022

  1. WWW
    Accelerating Serverless Computing by Harvesting Idle Resources
    Hanfei Yu, Hao Wang, Jian Li, Xu Yuan, and Seung-Jong Park
    In ACM Web Conference 2022, 2022
    Link

2021

  1. ACSOS
    FaaSRank: Learning to Schedule Functions in Serverless Platforms
    Hanfei Yu, Athirai A. Irissappane, Hao Wang, and Wes J. Lloyd
    In IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS), 2021
    Link
  2. ICPE
    Enhancing Observability of Serverless Computing with the Serverless Application Analytics Framework
    Robert Cordingly, Navid Heydari, Hanfei Yu, Varik Hoang, Zohreh Sadeghi, and Wes Lloyd
    In Companion of the ACM/SPEC International Conference on Performance Engineering, 2021
    Link
  3. WoSC
    The Serverless Application Analytics Framework: Enabling Design Trade-off Evaluation for Serverless Software
    Robert Cordingly, Hanfei Yu, Varik Hoang, Zohreh Sadeghi, David Foster, David Perez, Rashad Hatchett, and Wes Lloyd
    In The 2020 Sixth International Workshop on Serverless Computing, 2021
    Link

2020

  1. arXiv
    Leveraging GPT-2 for Classifying Spam Reviews with Limited Labeled Data via Adversarial Training
    Athirai A Irissappane, Hanfei Yu, Yankun Shen, Anubha Agrawal, and Gray Stanton
    arXiv preprint arXiv:2012.13400, 2020
    Link
  2. CBDCom
    Implications of Programming Language Selection for Serverless Data Processing Pipelines
    Robert Cordingly, Hanfei Yu, Varik Hoang, David Perez, David Foster, Zohreh Sadeghi, Rashad Hatchett, and Wes J Lloyd
    In IEEE International Conference on Cloud and Big Data Computing, 2020
    Link