Avatar of Ziwei Song

Ziwei Song

4th-year Ph.D. Student in Computer Science
Hong Kong SAR

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.

Real-Time Scheduling for MoE Inference Real-Time LLM Agent Scheduling LLM Agents for OS Kernel Formal Verification Autonomous Driving Systems Edge Intelligence
Full CV

// interactive lab

Deadline Drive

An autonomous car runs an MoE brain on a fixed memory budget. Keep the control loop on time.

WARMING UP
Cruise
4 / 8 in memory
tokens→router→top-2→experts —
p99 —

Hover or tap the underlined labels to see the paper behind each part.

Instruction
Policy
p99— deadline miss— expert hit— batch—
Earlier work

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.

  • City University of Hong Kong
    Department of Computer Science
    Ph.D. in Computer Science
    Jun. 2023 - Present
  • University of Electronic Science and Technology of China
    School of Information and Software Engineering
    M.S. in Software Engineering
    Sep. 2019 - Jun. 2022
  • University of Electronic Science and Technology of China
    School of Information and Software Engineering
    B.S. in Software Engineering
    Sep. 2015 - Jun. 2019
  • Chengdu Taiji Bear Technology Co., Ltd.
    FPGA Group
    Research Intern
    Jul. 2018 - Apr. 2019
  • International Technological University
    Embedded System Group
    Research Intern
    Jul. 2016 - Aug. 2016
  • Outstanding Graduate, Sichuan Province
    2022
  • Outstanding Graduate, University of Electronic Science and Technology of China
    2022
  • National Scholarship, Ministry of Education
    2021
2026
RT-MoE accepted to IEEE RTSS 2026. Read more
Jan 01
2025
Autoware.Flex presented at RTCSA 2025. Read more
Aug 20
2023
Started my Ph.D. at City University of Hong Kong, advised by Prof. Nan Guan.
Jun 01
RTSS
RT-MoE: Real-Time Expert Management for Memory-Constrained MoE Decoding

Ziwei Song, Ruoxiang Li, Fei Guan, Jen-Ming Wu, Jason Xue, Nan Guan

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

Ziwei Song, Ruoxiang Li, Fei Guan, Jen-Ming Wu, Jason Xue, Nan Guan

IEEE Real-Time Systems Symposium (RTSS) 2026 Accepted

Real-time expert management for mixture-of-experts decoding under tight memory budgets.

RTCSA
Autoware.Flex: Human-Instructed Dynamically Reconfigurable Autonomous Driving Systems

Ziwei Song, Mingsong Lv, Tianchi Ren, Chun Jason Xue, Jen-Ming Wu, Nan Guan

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

Ziwei Song, Mingsong Lv, Tianchi Ren, Chun Jason Xue, Jen-Ming Wu, Nan Guan

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.

TII
Layer-Wise Security Protection for Deep Neural Networks in Industrial Cyber Physical Systems

Wei Jiang, Ziwei Song, Jinyu Zhan, Di Liu, Jiafu Wan

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

Wei Jiang, Ziwei Song, Jinyu Zhan, Di Liu, Jiafu Wan

IEEE Transactions on Industrial Informatics (TII) 2022 Journal

A layer-wise security framework that protects DNN models deployed in industrial cyber-physical systems.

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.

Comics & Drama
Rick & Morty Family Honour One Piece Saint Seiya: The Hades Chapter
Mystery Novels
Agatha Christie John Dickson Carr Ellery Queen Arthur Conan Doyle Harlan Coben
Everything comes from the Liu & Layland boundary.