Xin Yin (ๆฎท้ซ) is the third-year Ph.D. student at Zhejiang University, supervised by Prof. Chao Ni. I also obtained Bachelorโs degree at Central South University.
My research interest includes Large Language Model, Software Testing, and Software Security. I have published papers at the top international conferences such as FSE/ISSTA/ICSE/CVPR. I developed a few well-known approaches including:
- SVulD and MVulD: Vulnerability Detection
- CodeGPTSensor+: LLM-generated Code Detection
- ThinkRepair: Program Repair
- Rectifier: Code Translation
- AUGER and RATester: Unit Test Generation
In 2025, I will lead or participate in the following research topics:
- Software Testing: Unit Test Generation
- Large Language Models (LLMs): Knowledge Editing
๐ฅ News
- 2025.02: ย ๐ One paper was accepted by CVPR 2025!
- 2024.10: ย ๐ One paper was accepted by ICSE 2025!
- 2024.09: ย ๐ One paper was accepted by TSE 2024!
- 2024.07: ย ๐ One paper was accepted by ISSTA 2024!
- 2023.05: ย ๐ One paper was accepted by FSE 2023!
๐ Selected Publications
# denotes co-first author or first student author
Preprints
- Detecting LLM-generated Code with Subtle Modification by Adversarial Training, Xin Yin, Xinrui Li, Chao Ni, Xiaodan Xu, Xiaohu Yang, Arxiv
- MulChain: Enabling Advanced Cross-Modal Queries in Hybrid-Storage Blockchains, Zhiyuan Peng, Xin Yin#, Gang Wang, Chenhao Ying, Wei Chen, Xikun Jiang, Yibin Xu, Yuan Luo, Arxiv
- SolEval: Benchmarking Large Language Models for Repository-level Solidity Smart Contract Generation, Zhiyuan Peng, Xin Yin#, Rui Qian, Peiqin Lin, Yongkang Liu, Chenhao Ying, Yuan Luo, Arxiv
- Enhancing LLMโs Ability to Generate More Repository-Aware Unit Tests Through Precise Contextual Information Injection, Xin Yin, Chao Ni, Xinrui Li, Liushan Chen, Guojun Ma, Xiaohu Yang, Arxiv
- Improving the Ability of Pre-trained Language Model by Imparting Large Language Modelโs Experience, Xin Yin, Chao Ni, Xiaodan Xu, Xinrui Li, Xiaohu Yang, Arxiv
- Learning-based Models for Vulnerability Detection: An Extensive Study, Chao Ni, Xin Yin#, Liyu Shen, Xiaodan Xu, Shaohua Wang, Arxiv
- Abundant Modalities Offer More Nutrients: Multi-Modal-Based Function-level Vulnerability Detection, Chao Ni, Xin Yin#, Xiaodan Xu, Arxiv
- Rectifier: Code Translation with Corrector via LLMs, Xin Yin, Chao Ni, Tien N. Nguyen, Shaohua Wang, Xiaohu Yang, Arxiv
- Pros and Cons! Evaluating ChatGPT on Software Vulnerability, Xin Yin, Arxiv
Peer-Reviewed
- Reasoning to Attend: Try to Understand How <SEG> Token Works, Rui Qian, Xin Yin, Dejing Dou, CVPR 2025, CCF-A
- What You See Is What You Get: Attention-based Self-guided Automatic Unit Test Generation, Xin Yin, Chao Ni, Xiaodan Xu, Xiaohu Yang, ICSE 2025, CCF-A
- Multitask-based Evaluation of Open-Source LLM on Software Vulnerability, Xin Yin, Chao Ni, Shaohua Wang, TSE 2024, CCF-A
- ThinkRepair: Self-Directed Automated Program Repair, Xin Yin, Chao Ni, Shaohua Wang, Zhenhao Li, Limin Zeng, Xiaohu Yang, ISSTA 2024, CCF-A
- Distinguishing Look-Alike Innocent and Vulnerable Code by Subtle Semantic Representation Learning and Explanation, Chao Ni, Xin Yin#, Kaiwen Yang, Dehai Zhao, Zhenchang Xing, Xin Xia, FSE 2023, CCF-A
๐ Educations
- 2022.09 - Present, Ph.D. student, Zhejiang University.
- 2018.09 - 2022.06, Bachelor, Central South University.
๐ป Internships
- 2024.06 - Present, State Key Laboratory of Blockchain and Data Security, Hangzhou.
- 2023.07 - 2023.10, Software Engineering Application Technology Lab at Huawei, Hangzhou.