Ma Ruhui, Ph.D., is an Associate Professor and Ph.D. Supervisor at the School of Computer Science, Shanghai Jiao Tong University. He is a key member of the State Key Laboratory Cultivation Base (jointly established by the province and ministry), the Shanghai Key Laboratory of Scalable Computing and Systems, and the Shanghai Joint Cloud Computing Laboratory. He has received the Shanghai Technical Invention Award (First Prize) and the Jiangsu Provincial Science and Technology Progress Award (Third Prize). He was honored with the Outstanding Contribution Award at CollaborateCom 2022 and has been supported by the Shanghai Jiao Tong University Postdoctoral Fellowship Program and the IBM Ph.D. Talent Program. Under his supervision, students have won the Second Prize in the National Mathematical Modeling Competition, the First Prize in the Shanghai Mathematical Modeling Competition, and the Second Prize in the Eastern Division of the China University Students Service Outsourcing Innovation and Entrepreneurship Competition. He has also supervised undergraduate students who were recognized as Outstanding Undergraduate Graduates of Shanghai Jiao Tong University (top 1%) and awarded the "Shanghai Jiao Tong University Zhiyuan Honors Ph.D. Program" scholarship. His course, "Restructuring Discrete Computing Teaching for the Electrical and Electronic Disciplines," was awarded the Second Prize in the Shanghai Jiao Tong University Teaching Achievement Awards.

Dr. Ma Ruhui’s research team focuses on the construction and optimization of distributed intelligent computing systems, primarily addressing three closely related and mutually supportive directions:

Direction 1: Distributed Computing (Federated Learning and Distributed Machine Learning Systems)
This direction aims to address collaborative machine learning challenges in the context of data silos and privacy protection. Core research includes the optimization of federated learning algorithms (e.g., personalization, robustness, communication efficiency, knowledge distillation), the design of federated learning frameworks (e.g., cross-domain, blockchain-assisted), and their applications in areas such as recommendation systems, smart agriculture, and intelligent transportation. Research outcomes have been published in top-tier CCF-A conferences (e.g., KDD, ICCV, NeurIPS) and leading journals (e.g., ACM ToIS, ACM RecSys).

Direction 2: Cloud Computing Systems (Serverless and Emerging Computing Paradigms)
This direction explores next-generation cloud computing paradigms centered on serverless computing. Research covers performance bottleneck mitigation in serverless systems (e.g., cold start optimization, I/O acceleration, resource scheduling), novel application architectures (e.g., stream processing, big data analytics, model serving), and integration with technologies such as edge computing and quantum computing. Research outcomes have been systematically published in CCF-A journals (e.g., TACO, TC, TPDS, JSAC) and conferences (e.g., DAC).

Direction 3: Large Models and System Optimization (Inference Optimization and Cross-Disciplinary Applications)
This direction focuses on the practical deployment and system-level support technologies for large models such as Large Language Models (LLMs). Research includes efficient inference of large models (e.g., memory optimization, pipeline parallelism, load balancing on edge devices), domain-specific applications, and the security and optimization of distributed systems supporting large model operations. Research outcomes have been published in CCF-A/B conferences (e.g., ACL, EMNLP, ICCD) and journals (e.g., TACO).