Shifan Liu

I am a Ph.D. student in Computer Science and Technology at the University of Science and Technology Beijing (USTB), supervised by Prof. Chang-ai Sun. My research focuses on software testing and quality assurance for deep learning frameworks and compilers, with particular interests in historical-defect-driven testing and AI-assisted software maintenance.

Research Interests

• Software Testing
• Deep Learning Framework and Compiler Quality Assurance
• Historical-Defect-Driven Testing

Publications

1. 2026
   SpectraDL: A Historical Issue-Driven, Test Specification-Assisted Transfer Testing Approach for Deep Learning Frameworks via LLMs
   Shifan Liu, Chang-ai Sun, Fulei Wu, and Wing-Kwong Chan.
   Proceedings of the ACM on Software Engineering, vol. 3, ISSTA, Article ISSTA103. Accepted research paper at ISSTA 2026. DOI: 10.1145/3832194.
2. 2026
   CPMT: A Collaborative Metamorphic Relations and Test Cases Prioritization Approach for Metamorphic Testing
   Chang-ai Sun, Shifan Liu, An Fu, and Jiaming Zhang.
   Information and Software Technology, vol. 190, Article 107975.
3. 2025
   SEOCD: Detecting Obsolete Code Comments by Fusing Semantic Features and Expert Features
   Zhanqi Cui, Shifan Liu, Li Li, and Liwei Zheng.
   Expert Systems with Applications, vol. 280, Article 127470.
4. 2024
   MMCUP: Automatic Code Comment Updating by Fusing Multimodal Information
   Shifan Liu, Zhanqi Cui, Xiang Chen, and Li Li.
   Chinese Journal of Computers, vol. 47, no. 1, pp. 172-189. In Chinese.
5. 2023
   TBCUP: A Transformer-Based Code Comments Updating Approach
   Shifan Liu, Zhanqi Cui, Xiang Chen, Jun Yang, Li Li, and Liwei Zheng.
   2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 892-897.

Education