Jiayang Song

5-362 Donadeo Innovation Centre for Engineering

9211 116 St NW

Edmonton, AB, Canada T6G 1H9

About Me

I am a Ph.D. candidate in the Department of Electrical and Computer Engineering, University of Alberta, supervised by Prof.Lei Ma. I received my M.Eng in Electrical and Computer Engineering with specialization in Machine Learning from the University of Toronto in 2021, B.Eng in Electrical and Computer Engineering from Western University in 2019. I am grateful for the support from the Alberta Machine Intelligence Institute (Amii) and Future Energy System (FES).

Research Interest

My primary research directions are oriented on Quality Assurance for Trustworthy AI systems such as AI-enabled Cyber-Physical systems (AI-CPS) and Foundation Models.

AI-CPS are integrated systems in which traditional software units, Artificial Intelligence (AI) components, and physical plants are intertwined to collaboratively perform complex tasks (e.g., Robotics, Energy Systems, Autonomous Driving). However, two questions keep me up at night and encourage me to explore further, namely, (1) How to safeguard the quality of sophisticated AI-CPS? and (2) What is the best practice of cyber-physical interaction?

My research is devoted to investigating these two questions in three stages: (1) design AI-aware testing and evaluation techniques to reveal the capability of AI-CPS, (2) propose novel analysis strategies to understand the behavior characteristics of AI components w.r.t. the physical world, and (3) develop enhancement solutions to improve the overall safety and reliability of the system across domains.

News

Dec 02, 2024	Our paper Look Before You Leap: An Exploratory Study of Uncertainty Analysis for Large Language Models is accepted at IEEE Transactions on Software Engineering (TSE).
Jul 10, 2024	Our preprint Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixtures is available on arXiv. This paper introduces Multilingual Blending, a mixed-language query-response scheme designed to evaluate the safety alignment of SOTA LLMs under sophisticated, code-switching conditions.

Selected Publications

LLM

Look before you leap: An exploratory study of uncertainty measurement for large language models

Yuheng Huang, Jiayang Song, Zhijie Wang, and 4 more authors

IEEE Transactions on Software Engineering., 2024

Bib PDF

@article{huang2023look,
  title = {Look before you leap: An exploratory study of uncertainty measurement for large language models},
  author = {Huang, Yuheng and Song, Jiayang and Wang, Zhijie and Zhao, Shengming and Chen, Huaming and Juefei-Xu, Felix and Ma, Lei},
  journal = {IEEE Transactions on Software Engineering.},
  year = {2024},
  organization = {IEEE},
}

AI-CPS

When cyber-physical systems meet AI: A benchmark, an evaluation, and a way forward

Jiayang Song, Deyun Lyu, Zhenya Zhang, and 3 more authors

In Proceedings of the 44th International Conference on Software Engineering: Software Engineering in Practice, 2022

Bib PDF

@inproceedings{song2022cyber,
  title = {When cyber-physical systems meet AI: A benchmark, an evaluation, and a way forward},
  author = {Song, Jiayang and Lyu, Deyun and Zhang, Zhenya and Wang, Zhijie and Zhang, Tianyi and Ma, Lei},
  booktitle = {Proceedings of the 44th International Conference on Software Engineering: Software Engineering in Practice},
  pages = {343--352},
  year = {2022},
}

AI-CPS

Towards building AI-CPS with NVIDIA Isaac sim: An industrial benchmark and case study for robotics manipulation

Zhehua Zhou, Jiayang Song, Xuan Xie, and 5 more authors

In Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice, 2024

Bib PDF

@inproceedings{zhou2024towards,
  title = {Towards building AI-CPS with NVIDIA Isaac sim: An industrial benchmark and case study for robotics manipulation},
  author = {Zhou, Zhehua and Song, Jiayang and Xie, Xuan and Shu, Zhan and Ma, Lei and Liu, Dikai and Yin, Jianxiong and See, Simon},
  booktitle = {Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice},
  pages = {263--274},
  year = {2024},
}

AI-CPS

SIEGE: A Semantics-Guided Safety Enhancement Framework for AI-Enabled Cyber-Physical Systems

Jiayang Song, Xuan Xie, and Lei Ma

IEEE Transactions on Software Engineering, 2023

Bib PDF

@article{song2023mathtt,
  title = {SIEGE: A Semantics-Guided Safety Enhancement Framework for AI-Enabled Cyber-Physical Systems},
  author = {Song, Jiayang and Xie, Xuan and Ma, Lei},
  journal = {IEEE Transactions on Software Engineering},
  volume = {49},
  number = {8},
  pages = {4058--4080},
  year = {2023},
  publisher = {IEEE},
}

LLM

LUNA: A Model-Based Universal Analysis Framework for Large Language Models

Da Song, Xuan Xie, Jiayang Song, and 4 more authors

IEEE Transactions on Software Engineering, 2024

Bib PDF

@article{song2024luna,
  title = {LUNA: A Model-Based Universal Analysis Framework for Large Language Models},
  author = {Song, Da and Xie, Xuan and Song, Jiayang and Zhu, Derui and Huang, Yuheng and Juefei-Xu, Felix and Ma, Lei},
  journal = {IEEE Transactions on Software Engineering},
  year = {2024},
  publisher = {IEEE},
}

Robotics-RL

GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model

Zhehua Zhou, Xuan Xie, Jiayang Song, and 2 more authors

IEEE Transactions on Neural Networks and Learning Systems, 2024

Bib PDF

@article{10766903,
  author = {Zhou, Zhehua and Xie, Xuan and Song, Jiayang and Shu, Zhan and Ma, Lei},
  journal = {IEEE Transactions on Neural Networks and Learning Systems},
  title = {GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model},
  year = {2024},
  publisher = {IEEE},
  pages = {1-15},
}