Xiuwei Shang  

Postgraduate

Information Processing Center (IPC) - System Security Group
University of Science & Technology of China (USTC)
Hefei, Anhui, China

Email: shangxw@mail.ustc.edu.cn; sxxxw010605@163.com
Github: Sxxxw

[Google Scholar] [DBLP]

Biography

Now I am a Postgraduate Student at Information Processing Center (IPC) in University of Science & Technology of China, supervised by Prof. Weiming Zhang and Assoc. Prof. Shaoyin Cheng. I received my B.S. degree of Computer Science and Technology from Dalian Maritime University in 2023, and was recommended to pursue a master's degree at the USTC in the same year.

From March 2021 to September 2023, I worked as an undergraduate research assistant in the TSMC Intelligent Software Engineering Laboratory, Dalian Maritime University, supervised by Assoc. Prof. Shikai Guo. Our laboratory also has close cooperation with Prof. He Jiang and Assoc. Prof. Xiaochen Li of Dalian University of Technology.

My research interests include AI(NLP/LLMs/Agent) for Software Engineering/Security, especially Binary/Source Code Representation, Understanding, and Analysis.

Now I am looking for a 2026 Fall PhD position. I would be thrilled if you are interested in my resume. Please feel free to contact me by email!

Education

Publications

(* indicates equal contribution)
  1. [TOSEM'25] FoC: Figure out the Cryptographic Functions in Stripped Binaries with LLMs IF2024: 6.6, CCF-A
    Xiuwei Shang*, Guoqiang Chen*, Shaoyin Cheng, Shikai Guo, Yanming Zhang, Weiming Zhang, Nenghai Yu
    ACM Transactions on Software Engineering and Methodology, 2025
  2. [TOSEM'24] Analyzing and Detecting Information Types of Developer Live Chat Threads IF2024: 6.6, CCF-A
    Xiuwei Shang, Shuai Zhang, Yitong Zhang, Shikai Guo, Yulong Li, Rong Chen, Hui Li, Xiaochen Li, He Jiang
    ACM Transactions on Software Engineering and Methodology, 2024
  3. [IJCAI'25] BinMetric: A Comprehensive Binary Code Analysis Benchmark for Large Language Models CCF-A
    Xiuwei Shang, Guoqiang Chen, Shaoyin Cheng, Benlong Wu, Li Hu, Gangyang Li, Weiming Zhang, Nenghai Yu
    The 34th International Joint Conference on Artificial Intelligence, 2025, Montreal, Canada
    [ArXiv]
  4. [ICSME'24] How Far Have We Gone in Binary Code Understanding Using Large Language Models CCF-B
    Xiuwei Shang, Shaoyin Cheng, Guoqiang Chen, Yanming Zhang, Li Hu, Xiao Yu, Gangyang Li, Weiming Zhang, Nenghai Yu
    The 40th International Conference on Software Maintenance and Evolution, 2024, Flagstaff, AZ, USA
  5. [ACL'25] CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System CCF-A
    Li Hu, Guoqiang Chen, Xiuwei Shang, Shaoyin Cheng, Benlong Wu, Gangyang Li, Xu Zhu, Weiming Zhang, Nenghai Yu
    The 63rd Annual Meeting of the Association for Computational Linguistics, Main Track, 2025
    [ArXiv]
  6. [EMNLP'24] RealVul: Can We Detect Vulnerabilities in Web Applications with LLM? CCF-B
    Di Cao, Yong Liao, Xiuwei Shang
    The 2024 Conference on Empirical Methods in Natural Language Processing, Main Track, 2024
  7. [NeurIPS'25] DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection CCF-A
    Xiao Yu, Yuang Qi, Kejiang Chen, Guoqiang Chen, Xi Yang, Pengyuan Zhu, Xiuwei Shang, Weiming Zhang, Nenghai Yu
    The 38th Annual Conference on Neural Information Processing Systems, 2024
    [ArXiv]
  8. [ACM MM'24] SemGIR: Semantic-Guided Image Regeneration based method for AI-generated Image Detection CCF-A
    Xiao Yu, Kejiang Chen, Kai Zeng, Han Fang, Zijin Yang, Xiuwei Shang, Yuang Qi, Weiming Zhang, Nenghai Yu
    The 32th ACM International Conference on Multimedia, 2024
  9. [PAAP'22] Do Not Have Enough Data? An Easy Data Augmentation for Code Summarization
    Zixuan Song, Xiuwei Shang, Mengxuan Li, Rong Chen, Hui Li, Shikai Guo
    IEEE 13th International Symposium on Parallel Architectures, Algorithms and Programming, Beijing, China, 2022
    Best Paper Runner-up Awards
  10. [NEUCOM'23] An Data Augmentation method for Source Code Summarization IF2023: 5.5, JCR-Q1
    Zixuan Song, Hui Zeng, Xiuwei Shang, Guanxi Li, Hui Li, Shikai Guo
    Neurocomputing, 2023

Preprints and under review

(* indicates equal contribution)
  1. [EMSE'25] An Empirical Study on the Effectiveness of Large Language Models for Binary Code Understanding IF2024: 3.5, CCF-B
    Xiuwei Shang, Zhenkan Fu, Shaoyin Cheng, Guoqiang Chen, Gangyang Li, Li Hu, Weiming Zhang, Nenghai Yu
    Empirical Software Engineering, 2025 (An invited extended version of the ICSME'24 paper)
  2. [TRel'25] Binary Code Similarity Detection via Graph Contrastive Learning on Intermediate Representations IF2024: 5, JCR-Q1
    Xiuwei Shang, Li Hu, Shaoyin Cheng, Shikai Guo, Guoqiang Chen, Benlong Wu, Weiming Zhang, Nenghai Yu
    IEEE Transactions on Reliability, 2025
    [ArXiv]
  3. [TOSEM'25] Beyond the Edge of Function: Unraveling the Patterns of Type Recovery in Binary Code IF2024: 6.6, CCF-A
    Gangyang Li, Xiuwei Shang, Shaoyin Cheng, Junqi Zhang, Li Hu, Xu Zhu, Weiming Zhang, Nenghai Yu
    ACM Transactions on Software Engineering and Methodology, 2025
    [ArXiv]
  4. [ESORICS'25] WelkIR: Flow-Sensitive Pretrained Embeddings from Compiler IR for Vulnerability Detection CCF-B
    Hao Huang, Xiuwei Shang, Junqi Zhang, Shaoyin Cheng, Weiming Zhang, Nenghai Yu
    The 30th European Symposium on Research in Computer Security, 2025
  5. [TIFS'25] AutoPT: How Far Are We from End2End Automated Pen-testing? CCF-A
    Benlong Wu, Guoqiang Chen, Kejiang Chen, Xiuwei Shang, Jiapeng Han, Yanru He, Weiming Zhang, Nenghai Yu
    IEEE Transactions on Information Forensics and Security, 2025
    [ArXiv]
  6. ['25] Dig in Shadow: Detecting Unexpected Communication Functions in Binaries via Code Representative Learning CCF-A
    Yanming Zhang, Shaoyin Cheng, Guoqiang Chen, Xiuwei Shang, Weiming Zhang, Nenghai Yu

Teaching Experience

Academic Services

External Reviewer

Honors & Awards

Competitions

© 2024.12.19 Xiuwei Shang