Computational Intelligence for Software Engineering Lab

Our research focuses on the exciting intersection between software engineering and machine intelligence. We try to improve developer productivity with optimisation and automation. COINSE has world-leading expertise in automated debugging, automated testing, and testing of DNN models.

Recent Updates

Our paper "Fonte: Finding Bug Inducing Commits from Failures" has been accepted at ICSE 2023

This paper is about finding bug-inducing commits by combining fault localisation and commit history mining. [more...]

Our paper "Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction" has been accepted to ICSE 2023

Our paper about generating bug-reproducing tests from bug reports was accepted to ICSE'23. [more...]

Our new paper "FDG: A Precise Measurement of Fault Diagnosability Gain of Test Cases" is accepted at ISSTA 2022

A COINSE paper about fault diagnosability gain has been accepted at ISSTA 2022. [more...]

Congratulations, Dr. Seongmin Lee!

Seongmin Lee successfully defended his PhD thesis, the second from from COINSE group. [more...]

A new paper about automatically augmenting equivalent mutant dataset has been accepted at MUTATION 2022

We present an automated technique to augment equivalent mutant dataset. [more...]

Our new paper "Automatically Identifying Shared Root Causes of Test Breakages in SAP HANA" is accepted to ICSE-SEIP 2022

We present a technique for identifying shared root causes of test breakages by combining multiple information sources associated with the failing tests. [more...]

Latest Publications

  1. The Inversive Relationship Between Bugs and Patches: An Empirical Study, Kim, J., Park, J. and Yoo, S., Proceedings of the 18th International Workshop on Mutation Analysis. [bibtex]
      @inproceedings{Kim2023pa,
      author = {Kim, Jinhan and Park, Jongchan and Yoo, Shin},
      booktitle = {Proceedings of the 18th International Workshop on Mutation Analysis},
      series = {MUTATION 2023},
      title = {The Inversive Relationship Between Bugs and Patches: An Empirical Study},
      year = {2023},
      month = apr
    }
    
    
  2. Repairing DNN Architecture: Are We There Yet?, Kim, J., Humbatova, N., Jahangirova, G., Tonella, P. and Yoo, S., Proceedings of the 16th IEEE International Conference on Software Testing, Verification and Validation. [bibtex]
      @inproceedings{Kim2023aa,
      author = {Kim, Jinhan and Humbatova, Nargiz and Jahangirova, Gunel and Tonella, Paolo and Yoo, Shin},
      booktitle = {Proceedings of the 16th IEEE International Conference on Software Testing, Verification and Validation},
      series = {ICST 2023},
      title = {Repairing DNN Architecture: Are We There Yet?},
      year = {2023}
    }
    
    
  3. Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction, Kang, S., Yoon, J. and Yoo, S., Proceedings of the 45th IEEE/ACM International Conference on Software Engineering. [pdf] [bibtex]
      @inproceedings{Kang2023aa,
      author = {Kang, Sungmin and Yoon, Juyeon and Yoo, Shin},
      booktitle = {Proceedings of the 45th IEEE/ACM International Conference on Software Engineering},
      series = {ICSE 2023},
      title = {Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction},
      year = {2023}
    }
    
    
  4. Fonte: Finding Bug Inducing Commits from Failures, An, G., Hong, J., Kim, N. and Yoo, S., Proceedings of the 45th IEEE/ACM International Conference on Software Engineering. [pdf] [bibtex]
      @inproceedings{An2023aa,
      author = {An, Gabin and Hong, Jingun and Kim, Naryeong and Yoo, Shin},
      booktitle = {Proceedings of the 45th IEEE/ACM International Conference on Software Engineering},
      series = {ICSE 2023},
      title = {Fonte: Finding Bug Inducing Commits from Failures},
      year = {2023}
    }
    
    
  5. Evaluating Surprise Adequacy for Deep Learning System Testing, Kim, J., Feldt, R. and Yoo, S., ACM Transactions on Software Engineering and Methodology, to appear: [bibtex]
      @article{Kim2022hg,
      address = {New York, NY, USA},
      author = {Kim, Jinhan and Feldt, Robert and Yoo, Shin},
      journal = {ACM Transactions on Software Engineering and Methodology},
      month = jun,
      publisher = {Association for Computing Machinery},
      series = {TOSEM},
      title = {Evaluating Surprise Adequacy for Deep Learning System Testing},
      volume = {to appear},
      year = {2022}
    }
    
    
  6. Augmenting Equivalent Mutant Dataset Using Symbolic Execution, Chung, S. and Yoo, S., Proceedings of the 2022 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), 150–159. [bibtex]
      @inproceedings{Chung2022uz,
      author = {Chung, Seungjun and Yoo, Shin},
      booktitle = {Proceedings of the 2022 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)},
      doi = {10.1109/ICSTW55395.2022.00038},
      issn = {2159-4848},
      month = apr,
      pages = {150-159},
      publisher = {IEEE Computer Society},
      title = {Augmenting Equivalent Mutant Dataset Using Symbolic Execution},
      url = {https://doi.ieeecomputersociety.org/10.1109/ICSTW55395.2022.00038},
      year = {2022}
    }
    
    
  7. Arachne: Search Based Repair of Deep Neural Networks, Sohn, J., Kang, S. and Yoo, S., ACM Transactions on Software Engineering Methodology, to appear: [pdf] [bibtex]
      @article{Sohn2022cr,
      author = {Sohn, Jeongju and Kang, Sungmin and Yoo, Shin},
      journal = {{ACM} {T}ransactions on {S}oftware {E}ngineering {M}ethodology},
      title = {Arachne: Search Based Repair of Deep Neural Networks},
      volume = {to appear},
      year = {2022}
    }