Zinuo Cai (蔡子诺)
 |
Zinuo Cai, Ph.D. Candidate |
About Me
I am a Ph.D. Candidate in the School of Computer Science at Shanghai Jiao Tong University, advised by Prof. Ruhui Ma at the AISIG Group. I received my B.S. degree from the School of Software at Shanghai Jiao Tong University in 2021, and I expect to graduate with my Ph.D. in March 2027.
My research spans three main areas:
Serverless Computing: FAASHARE (TPDS’26), AARC (DAC’25), Ephemera (TACO’25), SMORE (TPDS’25), FasDL (TC’24), SMSS (JSAC’23).
Large Model Inference: Hermes (ICCD’24), CellServe (TACO’26), MigMoE (ICPP’26).
Quantum Computing: FedCompass (ICASSP’26), HWDSQP (JSAC’25), QFI-Opt (SPE’25).
Education
Ph.D. Candidate in Computer Science, Shanghai Jiao Tong University, Sep. 2021 - Mar. 2027 (expected)
B.S. in Software Engineering, Shanghai Jiao Tong University, Sep. 2017 - Jun. 2021
Selected Papers
First Author (incl. Co-first Author)
Cai Z, Han X, Jiang N, et al. Hermes+: Adaptive Memory-Efficient Pipeline Inference for Large Models on Edge Devices[J]. ACM Transactions on Autonomous and Adaptive Systems, 2026.
Cai Z, Chen Z, Ma R, et al. SMSS: Stateful Model Serving in Metaverse With Serverless Computing and GPU Sharing[J]. IEEE Journal on Selected Areas in Communications, 2023.
Cai Z, Chen Z, Chen X, et al. SPSC: Stream Processing Framework Atop Serverless Computing for Industrial Big Data[J]. IEEE Transactions on Cybernetics, 2024.
Cai Z, Chen Z, Liu Z, et al. RIDIC: Real-Time Intelligent Transportation System With Dispersed Computing[J]. IEEE Transactions on Intelligent Transportation Systems, 2023.
Cai Z, Yuan J, Hua Y, et al. Themis: A Fair Evaluation Platform for Computer Vision Competitions[C]. Proc. of the International Joint Conference on Artificial Intelligence (IJCAI), 2021.
Co-first Author (Second Position)
Jiang Z, Cai Z, Liu Y, et al. FAASHARE: Enabling Generic Low-Latency and SLO-Aware GPU Sharing in Serverless Computing[J]. IEEE Transactions on Parallel and Distributed Systems, 2026.
Jin L, Cai Z, Chen Z, et al. AARC: Automated Affinity-aware Resource Configuration for Serverless Workflows[C]. Proc. of the Design Automation Conference (DAC), 2025.
Jin L, Cai Z, Wang H, et al. Ephemera: Accelerating I/O-Intensive Serverless Workloads with a Harvested In-memory File System[J]. ACM Transactions on Architecture and Code Optimization, 2025.
Liu J, Cai Z, Liu Y, et al. SMORE: Enhancing GPU Utilization in Deep Learning Clusters by Serverless-based Co-location Scheduling[J]. IEEE Transactions on Parallel and Distributed Systems, 2025.
Chen X, Cai Z, Zhang H, et al. FasDL: An Efficient Serverless-Based Training Architecture with Communication Optimization and Resource Configuration[J]. IEEE Transactions on Computers, 2024.