Qinyun Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qinyun Wu has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Chao Peng
Bytedance, Beijing, China
3 shared publications - Bo Jiang
ByteDance, Shenzhen, China
2 shared publications - Ping Yang
Bytedance, Beijing, China
2 shared publications - Cuiyun Gao
Harbin Institute of Technology, Shenzhen, China
1 shared publication - Ji Luo
Tencent, Shenzhen, China
1 shared publication - Jiangchao Liu
ByteDance, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1973-1985
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1973-1985
Open AccessRepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
- Open Access
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3025-3029
Understanding Large Language Model Performance in Software Engineering: A Large-scale Question Answering Benchmark
- 13 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 3025-3029
Open AccessUnderstanding Large Language Model Performance in Software Engineering: A Large-scale Question Answering Benchmark
- Open Access
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2279-2283
RepoSim: Evaluating Prompt Strategies for Code Completion via User Behavior Simulation
Large language models (LLMs) have revolutionized code completion tasks. IDE plugins such as MarsCode can generate code recommendations, saving developers significant time and effort. However, current evaluation methods for code completion are limited by their reliance on static code benchmarks, which do not consider human interactions and evolving repositories. This paper proposes RepoSim, a novel benchmark designed to evaluate code completion tasks by simulating the evolving process of repositories and incorporating user behaviors. RepoSim leverages data from an IDE plugin, by recording and replaying user behaviors to provide a realistic programming context for evaluation. This allows for the assessment of more complex prompt strategies, such as utilizing recently visited files and incorporating user editing history. Additionally, RepoSim proposes a new metric based on users' acceptance or rejection of predictions, offering a user-centric evaluation criterion. Our preliminary evaluation demonstrates that incorporating users' recent edit history into prompts significantly improves the quality of LLM-generated code, highlighting the importance of temporal context in code completion. RepoSim represents a significant advancement in benchmarking tools, offering a realistic and user-focused framework for evaluating code completion performance.
- 27 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 2279-2283
Open AccessRepoSim: Evaluating Prompt Strategies for Code Completion via User Behavior Simulation
Large language models (LLMs) have revolutionized code completion tasks. IDE plugins such as MarsCode can generate code recommendations, saving developers significant time and effort. However, current evaluation methods for code completion are limited by their reliance on static code benchmarks, which do not consider human interactions and evolving repositories. This paper proposes RepoSim, a novel benchmark designed to evaluate code completion tasks by simulating the evolving process of repositories and incorporating user behaviors. RepoSim leverages data from an IDE plugin, by recording and replaying user behaviors to provide a realistic programming context for evaluation. This allows for the assessment of more complex prompt strategies, such as utilizing recently visited files and incorporating user editing history. Additionally, RepoSim proposes a new metric based on users' acceptance or rejection of predictions, offering a user-centric evaluation criterion. Our preliminary evaluation demonstrates that incorporating users' recent edit history into prompts significantly improves the quality of LLM-generated code, highlighting the importance of temporal context in code completion. RepoSim represents a significant advancement in benchmarking tools, offering a realistic and user-focused framework for evaluating code completion performance.
- Open Access
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 104-114
Neat: Mobile App Layout Similarity Comparison Based on Graph Convolutional Networks
A wide variety of device models, screen resolutions and operating systems have emerged with recent advances in mobile devices. As a result, the graphical user interface (GUI) layout in mobile apps has become increasingly complex due to this market fragmentation, with rapid iterations being the norm. Testing page layout issues under these circumstances hence becomes a resource-intensive task, requiring significant manpower and effort due to the vast number of device models and screen resolution adaptations. One of the most challenging issues to cover manually is multi-model and cross-version layout verification for the same GUI page. To address this issue, we propose Neat, a non-intrusive end-to-end mobile app layout similarity measurement tool that utilizes computer vision techniques for GUI element detection, layout feature extraction, and similarity metrics. Our empirical evaluation and industrial application have demonstrated that our approach is effective in improving the efficiency of layout assertion testing and ensuring application quality.
- 10 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 104-114
Open AccessNeat: Mobile App Layout Similarity Comparison Based on Graph Convolutional Networks
A wide variety of device models, screen resolutions and operating systems have emerged with recent advances in mobile devices. As a result, the graphical user interface (GUI) layout in mobile apps has become increasingly complex due to this market fragmentation, with rapid iterations being the norm. Testing page layout issues under these circumstances hence becomes a resource-intensive task, requiring significant manpower and effort due to the vast number of device models and screen resolution adaptations. One of the most challenging issues to cover manually is multi-model and cross-version layout verification for the same GUI page. To address this issue, we propose Neat, a non-intrusive end-to-end mobile app layout similarity measurement tool that utilizes computer vision techniques for GUI element detection, layout feature extraction, and similarity metrics. Our empirical evaluation and industrial application have demonstrated that our approach is effective in improving the efficiency of layout assertion testing and ensuring application quality.