Wang, Zhijie

Wang, Zhijie

University of Alberta

Zhijie Wang (王智杰)

Ph.D. Student

University of Alberta & Alberta Machine Learning Institute

5-362 Donadeo Innovation Centre for Engineering (DICE)

9211 116 St NW, Edmonton, AB T6G 1H9

Email: {First Name} dot {Last Name} at {University} dot ca

Short Bio

I am now a Ph.D. student in the Momentum Lab, Dept. of ECE, University of Alberta, supervised by Prof. Lei Ma. I received my M.Eng in Electrical and Computer Engineering with specialization in ML&AI from the University of Waterloo in Dec 2020, B.Eng in Telecommunication Engineering from Beijing University of Posts and Telecommunications (BUPT) in Jun 2019. During my undergraduate study, I got a chance to work with Prof. Ben M. Chen, and visit Prof. Chen’s group at National University of Singapore for 3 months.


BUPT
UWaterloo
UAlberta


* Up-to-date CV is available upon request.

My first name is 智杰 (Zhi Jie), pronounced /ʈʂɚ/ /tɕjɛ/, similar to (Chih-Chieh). Just call me Paul if you feel it is difficult to pronounce.

Research Interests

My current research interest focuses on Software Engineering (SE) support for complex AI-based software systems. My most recent works cover software testing, analysis, and repair for AI models and systems. Besides, I am also interested in the intersection of Software Engineering, AI, and Human-Computer Interaction (HCI). I design and develop interactive interfaces to help developers interpret and debug AI-based software.

  • Our work on the robustness benchmark of complex AI-based software and systems reveals their vulnerabilities, calling for researchers’ and practitioners’ attention to build trustworthy AI systems ([ICSE 2022, FSE 2023, TMM 2023]).

  • Our work on AI system analysis and its repair helps developers decouple complex AI systems and identify root causes of incorrect system behavior, solving critical robustness and reliability issues for our industrial partners ([TOSEM 2023]).

  • Our work on interactive interfaces for debugging AI-based software and its data at scale helps both novice and experienced developers identify potential software bugs with enriched feedback loops and interpretability ([CHI 2023a, CHI 2023b]).

Publications

Journal & Conference Proceedings

  • [TMM ‘23] Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancement
    Shuangzhi Li, Zhijie Wang, Felix Juefei-Xu, Qing Guo, Xingyu Li, Lei Ma
    IEEE Transactions on Multimedia. [CORE Rank A*]
    Pre-print

  • [FSE ‘23] Benchmarking Robustness of AI-enabled Multi-sensor Fusion Systems: Challenges and Opportunities
    Xinyu Gao, Zhijie Wang, Yang Feng, Lei Ma, Zhenyu Chen, Baowen Xu
    2023 ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. [CORE Rank A*]
     Pre-print     Project

  • [TOSEM ‘23] ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks
    Hua Qi*, Zhijie Wang*, Qing Guo, Jianlang Chen, Felix Juefei-Xu, Fuyuan Zhang, Lei Ma, Jianjun Zhao (* equal contribution)
    ACM Transactions on Software Engineering. [CORE Rank A*]
     Pre-print     Project

  • [CHI ‘23] DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction
    Zhijie Wang, Yuheng Huang, Da Song, Lei Ma, Tianyi Zhang
    In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ‘23). Article 740, 1–20. [CORE Rank A*]
    CHI2023a
     Paper     Code     Preview     Demo      Presentation

  • [CHI ‘23] DeepLens: Interactive Out-of-distribution Data Detection in NLP Models
    Da Song*, Zhijie Wang*, Yuheng Huang, Lei Ma, Tianyi Zhang (* equal contribution)
    In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems (CHI ‘23). Article 739, 1–17. [CORE Rank A*]
    CHI2023b
     Paper     Code     Preview      Demo      Presentation

  • [ICSE ‘22] When Cyber-Physical Systems Meet AI: A Benchmark, an Evaluation, and a Way Forward
    Jiayang Song, Deyun Lyu, Zhenya Zhang, Zhijie Wang, Tianyi Zhang, Lei Ma
    In Proceedings of 2022 IEEE/ACM 44th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), pp. 343-352 [CORE Rank A*]
     Paper     Code     Project

Pre-print

  • Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models
    Yuheng Huang, Jiayang Song, Zhijie Wang, Huaming Chen, Lei Ma
    Pre-print

  • Is Model Attention Aligned with Human Attention? An Empirical Study on Large Language Models for Code Generation
    Bonan Kou, Shengmai Chen, Zhijie Wang, Lei Ma, Tianyi Zhang
    Pre-print

  • An Exploratory Study of AI System Risk Assessment from the Lens of Data Distribution and Uncertainty
    Zhijie Wang, Yuheng Huang, Lei Ma, Haruki Yokoyama, Susumu Tokumoto, Kazuki Munakata
    Pre-print

  • CarveNet: Carving Point-Block for Complex 3D Shape Completion
    Qing Guo*, Zhijie Wang*, Felix Juefei-Xu, Di Lin, Lei Ma, Wei Feng, Yang Liu (* equal contribution)
    Pre-print

Talks

  • Invited Talk: Human-Centred Interactive Design for Data-Driven AI Software June 2023, Beihang University, Beijing

  • Invited Talk: Human-Centred Interactive Design for Data-Driven AI Software June 2023, Institute of Information Engineering, CAS, Beijing

  • ECE 720 Guest Lecture: Human-Centred Interactive Design for Data-Driven AI Software March 2023, University of Alberta, Edmonton, AB

  • Tutorial on AI Quality Assurance @ SEMLA2022 Oct 2023, Montreal, QC ( Material)

  • Tutorial on AI Quality Assurance @ ASE2022 Oct 2023, Michigan, USA (Remote, Material)

Industry

  • Joint Research Project @ Fujitsu Research, Tokyo (Remote) 2021-2022

  • Research Intern @ Megvii Research, Beijing 2018-2019

Teaching

@ University of Alberta (Lecture or Lab TA)

  • ECE 422 Reliable and Secure Systems Design (Winter 2023)

  • ECE 325 Object-Oriented Software Design (Fall 2021, 2022)

  • ECE 321 Software Requirements Engineering (Fall 2022)

  • ECE 720 Advanced Topics in Software Engineering and Intelligent Systems (Winter 2022, 2023)

  • ECE 380 Introduction to Communication Systems(Winter 2021).

@ University of Waterloo (Lecture TA)

  • ECE 203 Probability Theory and Statistics 1 (Spring 2020).

Service

Program Committee

ESEC/FSE 2023 Artifact Evaluation

Review

Conference: ICML 2022, NeurIPS 2022

Conference Sub-Review: QSR 2021/2022, ISSRE 2022, ASE 2022

Journal: IEEE Transactions on Reliability

Others

Student Volunteer, MODELS 2021

Misc.

When I’m not in the office, you can usually find me in a hockey rink (Go Bears Go! 🟢🟡 / Let’s go Oilers! 🟠🔵), in a concert, in a ski resort…

I love taking photos when traveling (an amateur photographer lol), you can find some of them here.

Acknowledgment

My research has been supported by

  • Alberta Machine Intelligence Institute (Amii)

  • Canadian Institute for Advanced Research (CIFAR)

  • Fujitsu Research