2 citations · 4 across the 4 of their papers we have counts for
4 papers
MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution
Yibo Wang, Zhihao Peng, Ying Wang +3
LLMs demonstrate strong performance in auto-mated software engineering, particularly for code generation and issue resolution. While proprietary models like GPT-4o achieve high ben…
Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting
Tsz-On Li, Wenxi Zong, Yibo Wang +4
Automatically detecting software failures is an important task and a longstanding challenge. It requires finding failure-inducing test cases whose test input can trigger the softwa…
Aper: Evolution-Aware Runtime Permission Misuse Detection for Android Apps
Sinan Wang, Yibo Wang, Xian Zhan +4
The Android platform introduces the runtime permission model in version 6.0. The new model greatly improves data privacy and user experience, but brings new challenges for app deve…
Runtime Permission Issues in Android Apps: Taxonomy, Practices, and Ways Forward
Ying Wang, Yibo Wang, Sinan Wang +5
Android introduces a new permission model that allows apps to request permissions at runtime rather than at the installation time since 6.0 (Marshmallow, API level 23). While this…