Ziwei Song
About Me
I am a 4th-year Ph.D. student in the Department of Computer Science at City University of Hong Kong, advised by Prof. Nan Guan, and a member of CityU MLab. My research sits at the intersection of real-time systems and AI: making large-model inference — especially mixture-of-experts — predictable under tight memory and latency budgets, and building autonomous driving systems that can be reconfigured on the fly. More recently, I have been exploring real-time scheduling of LLM agents and LLM agents for OS-kernel formal verification.
Prior to my Ph.D., I received my B.S. and M.S. degrees in Software Engineering from the University of Electronic Science and Technology of China in 2019 and 2022.
// interactive lab
Deadline Drive
An autonomous car runs an MoE brain on a fixed memory budget. Keep the control loop on time.
Hover or tap the underlined labels to see the paper behind each part.
Try Avoid cyclist with 2 experts at 30 ms — or switch to LRU and watch the tail.
What am I looking at?
Each control tick sends a batch of tokens from the car to a mixture-of-experts model. Only a few experts fit in memory; loading an absent expert adds latency. If the total exceeds the control deadline, the car hesitates.
LRU evicts the least recently used expert. RT-MoE protects hot experts and uses free slots for prefetch.
Inspired by Autoware.Flex (RTCSA 2025) and RT-MoE (RTSS 2026). This is an illustrative simulation, not a benchmark.
Education
-
City University of Hong KongDepartment of Computer Science
-
University of Electronic Science and Technology of ChinaSchool of Information and Software Engineering
-
University of Electronic Science and Technology of ChinaSchool of Information and Software Engineering
Experience
-
Chengdu Taiji Bear Technology Co., Ltd.FPGA Group
-
International Technological UniversityEmbedded System Group
Honors & Awards
-
Outstanding Graduate, Sichuan Province2022
-
Outstanding Graduate, University of Electronic Science and Technology of China2022
-
National Scholarship, Ministry of Education2021
News
Selected Publications view all
RT-MoE: Real-Time Expert Management for Memory-Constrained MoE Decoding
IEEE Real-Time Systems Symposium (RTSS) 2026 Accepted
Real-time expert management for mixture-of-experts decoding under tight memory budgets.
RT-MoE: Real-Time Expert Management for Memory-Constrained MoE Decoding
IEEE Real-Time Systems Symposium (RTSS) 2026 Accepted
Real-time expert management for mixture-of-experts decoding under tight memory budgets.
Autoware.Flex: Human-Instructed Dynamically Reconfigurable Autonomous Driving Systems
IEEE 31st International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA) 2025 Conference
A human-instructed, dynamically reconfigurable autonomous driving system built on the Autoware stack.
Autoware.Flex: Human-Instructed Dynamically Reconfigurable Autonomous Driving Systems
IEEE 31st International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA) 2025 Conference
A human-instructed, dynamically reconfigurable autonomous driving system built on the Autoware stack.
Layer-Wise Security Protection for Deep Neural Networks in Industrial Cyber Physical Systems
IEEE Transactions on Industrial Informatics (TII) 2022 Journal
A layer-wise security framework that protects DNN models deployed in industrial cyber-physical systems.
Layer-Wise Security Protection for Deep Neural Networks in Industrial Cyber Physical Systems
IEEE Transactions on Industrial Informatics (TII) 2022 Journal
A layer-wise security framework that protects DNN models deployed in industrial cyber-physical systems.
Beyond Research
In my first year as a master's student, I came across a paper on semi-federated scheduling of real-time systems — and decided then and there that I wanted to do real-time scheduling and publish a paper at RTSS. Years later, I never became a pure real-time scheduling theory person, but I am still working every day toward becoming a real-time systems researcher.