About Me

I am an Assistant Professor at the Faculty of Engineering and Applied Science, Ontario Tech University. Prior to that, I was a Postdoctoral Research Fellow at the University of Waterloo. I received my Ph.D. from Software Analysis and Intelligence Lab (SAIL) at Queen’s University under the supervision of Prof. Ahmed E. Hassan. I obtained my Master’s degree from Concordia University under the supervision of Prof. Weiyi Shang. My research interests include AIOps, software log management, log analytics, performance engineering, software testing, empirical software engineering, and mining software repositories. Contact me at kundi.yao@ontariotechu.ca

Publications

• World of Logs: A Dataset of Logs from Online Documents

  Xiaohui Wang, Kundi Yao, Lizhi Liao, Pengyu Nie, Xuan Zhang, Weiyi Shang.

  The 23rd International Mining Software Repositories Conference (MSR 2026), Data Track

• LPB-Gen: Systematic Large Log-Parsing Benchmarks Generation

  Hetong Dai, Kundi Yao, Felix Li, Jianxin You, Qianyun Shen, Weiyi Shang.

  ACM Transactions on Software Engineering and Methodology (TOSEM)

• Towards Secure Logging: Characterizing and Benchmarking Logging Code Security Issues with LLMs

  He Yang Yuan, Xin Wang, Kundi Yao, An Ran Chen, Zishuo Ding, Zhenhao Li

  The 34th ACM SIGSOFT Conference on the Foundations of Software Engineering (FSE 2026)

• LLM4JMH: Studying the Use of LLMs for Generating Java Performance Microbenchmarks

  Zongxiong Chen, Derui Zhu, Kundi Yao, Weiyi Shang, Jinfu Chen, Jiahui Geng, Alexander Pretschner, Jens Grossklags, Manfred Hauswirth, Sonja Schimmler

  The 48th IEEE/ACM International Conference on Software Engineering (ICSE 2026)

• An Empirical Study of Privacy Leakage Vulnerability in Third-Party Android Logs Libraries

  Yixi Zhao, Kundi Yao, Yiming Tang, Weiyi Shang

  The 33rd IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER 2026)

• Detecting DTC Requirement-Implementation Inconsistencies Using LLMs: An Experience Report

  Tongwei Zhang, Kundi Yao, Hanyang Hu, Pengyu Nie, Krishna Koravadi, Weiyi Shang

  IEEE Software

• Who’s to Blame? Rethinking the Brittleness of Automated Web GUI Testing from a Pragmatic Perspective

  Haonan Zhang, Kundi Yao, Zishuo Ding, Lizhi Liao, Weiyi Shang

  The 40th IEEE/ACM International Conference on Automated Software Engineering (ASE 2025)

• MEMCAIN: A Memory-Enhanced Hybrid CNN-Attention Model for Network Anomaly Detection

  Lan Liu, Tingfeng Cai, Chiyu Zhou, Fengwei Guo, Kundi Yao, Jianhao Zhou

  Springer Nature Scientific Reports (SREP 2025)

• An Empirical Study of Logging Practice in CUDA-based Deep Learning Systems

  An Chen, Kundi Yao, Haonan Zhang, Yiming Tang, Weiyi Shang

  The 25th IEEE International Conference on Software Quality, Reliability, and Security (QRS 2025)

• Improving QA System Testing Efficiency Through White-Box Test Prioritization

  Hanying Shao, Zishuo Ding, Kundi Yao, Haonan Zhang, Weiyi Shang.

  The 25th IEEE International Conference on Software Quality, Reliability, and Security (QRS 2025)

• Batch Execution of Microbenchmarks for Efficient Performance Testing

  Mostafa Jangali, Kundi Yao, Yiming Tang, Diego Elias Costa, and Weiyi Shang.

  The 18th IEEE International Conference on Software Testing, Verification and Validation (ICST 2025), Vision and Emerging Results.

• Finding associations between natural and computer languages: A case-study of bilingual LDA applied to the bleeping computer forum posts

  Kundi Yao, Gustavo A Oliva, Ahmed E. Hassan, Muhammad Asaduzzaman, Andrew J. Malton, Andrew Walenstein

  Journal of Systems and Software (JSS)

• Improving state-of-the-art compression techniques for log management tools

  Kundi Yao, Mohammed Sayagh, Weiyi Shang, and Ahmed E. Hassan

  IEEE Transactions on Software Engineering (TSE)

• A study of the performance of general compressors on log files

  Kundi Yao, Heng Li, Weiyi Shang, Ahmed E. Hassan

  Empirical Software Engineering (EMSE)

• Log4Perf: Suggesting and updating logging locations for web-based systems’ performance monitoring

  Kundi Yao, Guilherme B. de Pádua, Weiyi Shang, Catalin Sporea, Andrei Toma, Sarah Sajedi

  Empirical Software Engineering (EMSE)

• Log4perf: Suggesting logging locations for web-based systems’ performance monitoring

  Kundi Yao, Guilherme B. de Pádua, Weiyi Shang, Catalin Sporea, Andrei Toma, Sarah Sajedi

  The 9th ACM/SPEC International Conference on Performance Engineering (ICPE 2018). Best paper nomination.

Academic Services

• Program chair:
  • LTB 2026
• Program committee member:
  • ICPC 2026 (RENE Track)
  • FSE 2026 (Industry Track)
  • LLM4Code 2026
  • SANER 2026 (Research Track)
  • ISSRE 2025 (Artifact Evaluation Track)
  • AIware 2025 (Main Track)
  • SANER 2025 (Tool Demo Track)
  • ICPC 2025 (RENE Track)
  • LTB 2025
  • PROMISE 2025
• Reviewer: ASE, SPE, ICPE, SANER, ICPC, EMSE, PROMISE, IEEE Software, LTB, AIware.

Industrial experiences

• Research Collaborator (2024.04 - 2025.03)

  Wind River (Remote)

  Topics: Large language model (LLM), Requirement Engineering

• Research Intern (2023.01 - 2023.08)

  Blackberry Ltd, Waterloo, ON, Canada

  Topics: Large language model (LLM), RAG-based Code Generation, Predictive Analytics, Personally Identifiable Information (PII) Detection

• Research Intern (2020.05 - 2020.08)

  Blackberry Ltd (Remote)

  Topics: Natural Lanugage Processing (NLP), Log Analysis

• Research Intern (2017.01 - 2018.08)

  ERA Environmental Management Solutions, Montreal, QC, Canada

  Topics: Performance Modeling, Performance Testing

Invited Talks

• Consortium for Software Engineering Research (CSER 2024), Kingston, Canada. Improving state-of-the-art compression techniques for log management tools
• Blackberry Ltd, Waterloo, Canada (2021). Log Compression Techniques: Evaluation of Compression Options and New Approach to Preprocessing for Improved Compression
• The 9th ACM/SPEC International Conference on Performance Engineering (ICPE 2018), Berlin, Gemany. Log4perf: Suggesting logging locations for web-based systems’ performance monitoring