Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Haoyu Gao — PhD Candidate at the University of Melbourne
PhD candidate researching documentation maintenance and knowledge acquisition in software engineering at the University of Melbourne.
Page not in menu
This is a page not in th emain menu
Posts
portfolio
publications
Evaluating Transfer Learning for Simplifying GitHub READMEs
Published in ESEC/FSE 2023, 2023
Recommended citation: Haoyu Gao, Christoph Treude, and Mansooreh Zahedi. 2023. Evaluating Transfer Learning for Simplifying GitHub READMEs. In Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2023). Association for Computing Machinery, New York, NY, USA, 1548–1560. https://dl.acm.org/doi/abs/10.1145/3611643.3616291
Documenting Ethical Considerations in Open Source AI Models
Published in ESEM 2024, 2024
Recommended citation: Haoyu Gao, Mansooreh Zahedi, Christoph Treude, Sarita Rosenstock, and Marc Cheong. 2024. Documenting Ethical Considerations in Open Source AI Models. In ESEM 2024: 18th International Symposium on Empirical Software Engineering and Measurement. https://dl.acm.org/doi/abs/10.1145/3674805.3686679
Adapting Installation Instructions in Rapidly Evolving Software Ecosystems
Published in IEEE Transactions on Software Engineering, 2025
Recommended citation: Haoyu Gao, Christoph Treude, and Mansooreh Zahedi. 2025. Adapting Installation Instructions in Rapidly Evolving Software Ecosystems. IEEE Transactions on Software Engineering. https://ieeexplore.ieee.org/abstract/document/10931854
AI Failures in the Eyes of the Downstream Developer: A First Look at Concerns, Practices, and Challenges
arXiv preprint (Major Revision at EMSE), 2025
Recommended citation: Haoyu Gao, Mansooreh Zahedi, Wenxin Jiang, Hong Yi Lin, James C. Davis, and Christoph Treude. 2025. AI Failures in the Eyes of the Downstream Developer: A First Look at Concerns, Practices, and Challenges. arXiv:2503.19444. https://arxiv.org/abs/2503.19444
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models
Published in Findings of ACL 2025, 2025
Recommended citation: Huili Lin, Changlin Liu, Haoyu Gao, Patanamon Thongtanunam, and Christoph Treude. 2025. CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models. In Findings of ACL 2025: The 63rd Annual Meeting of the Association for Computational Linguistics. https://arxiv.org/abs/2503.16167
From Release to Adoption: Challenges in Reusing Pre-trained AI Models for Downstream Developers
Published in ICSME 2025, 2025
Recommended citation: Purit Banyongrakkul, Mansooreh Zahedi, Patanamon Thongtanunam, Christoph Treude, and Haoyu Gao. 2025. From Release to Adoption: Challenges in Reusing Pre-trained AI Models for Downstream Developers. In ICSME 2025: 41st International Conference on Software Maintenance and Evolution. https://arxiv.org/abs/2506.23234
Does My README File Need To Be Updated? Exploring LLM-Based README Maintenance
arXiv preprint (Major Revision at IEEE TSE), 2026
Recommended citation: Haoyu Gao, Hong Yi Lin, Christoph Treude, Gregory Gay, and Mansooreh Zahedi. 2026. Does My README File Need To Be Updated? Exploring LLM-Based README Maintenance. arXiv:2603.00489. https://arxiv.org/abs/2603.00489
Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision
arXiv preprint (under submission), 2026
Recommended citation: Hong Yi Lin, Chunhua Liu, Haoyu Gao, Patanamon Thongtanunam, and Christoph Treude. 2026. Fine-grained Approaches for Confidence Calibration of LLMs in Automated Code Revision. arXiv:2604.06723. https://arxiv.org/abs/2604.06723
When AI Models Become Dependencies: Studying the Evolution of Pre-Trained Model Reuse in Downstream Software Systems
arXiv preprint (under submission), 2026
Recommended citation: Peerachai Banyongrakkul, Mansooreh Zahedi, Christoph Treude, Haoyu Gao, and Patanamon Thongtanunam. 2026. When AI Models Become Dependencies: Studying the Evolution of Pre-Trained Model Reuse in Downstream Software Systems. arXiv:2604.17940. https://arxiv.org/abs/2604.17940
On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source
Published in MSR 2026, 2026
Recommended citation: Haoyu Gao, Peerachai Banyongrakkul, Hao Guan, Mansooreh Zahedi, and Christoph Treude. 2026. On Autopilot? An Empirical Study of Human-AI Teaming and Review Practices in Open Source. Short Paper in MSR 2026: 23rd International Conference on Mining Software Repositories. https://arxiv.org/abs/2601.13754
From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained
arXiv preprint, 2026
Recommended citation: Haoyu Gao, Jai Lal Lulla, Hong Yi Lin, Sebastian Baltes, Christoph Treude, and Mansooreh Zahedi. 2026. From Registry to Repository: How AI Agent Skills Are Written, Adapted, and Maintained. arXiv:2607.00911. https://arxiv.org/abs/2607.00911