Published several papers, including 'Efficient Data Passing for Serverless Inference Workflows: A GPU-Centric Approach' (EuroSys 2026), 'Toppings: CPU-Assisted, Rank-Aware Adapter Serving for LLM Inference' (USENIX ATC 2025), 'Torpor: GPU-Enabled Serverless Computing for Low-Latency, Resource-Efficient Inference' (USENIX ATC 2025), 'Pheromone: Restructuring Serverless Computing with Data-Centric Function Orchestration' (IEEE/ACM Transactions on Networking, 2024), 'Following the Data, Not the Function: Rethinking Function Orchestration in Serverless Computing' (USENIX NSDI 2023), 'Gillis: Serving Large Neural Networks in Serverless Functions with Automatic Model Partitioning' (IEEE ICDCS 2021, Best Paper Runner Up). Awarded CCF-Huawei Populus Grove Fund.
Research Experience
Assistant Professor at School of Data Science, The Chinese University of Hong Kong, Shenzhen. Published multiple papers in top conferences and journals, and served as a program committee member for several international conferences.
Education
PhD from Hong Kong University of Science and Technology, advised by Prof. Wei Wang; B.Eng. in Software Engineering from Nanjing University.
Background
Research interests cover the broad area of cloud computing and distributed systems, with a special focus on serverless computing, big data, and machine learning systems. Current research projects include: scalable ML and LLM inference systems, intelligent cluster management on heterogeneous resources, usable and efficient serverless computing platforms.