Yifeng Di

Ph.D. Student @ Purdue CS

Department of Computer Science

305 N. University Street

West Lafayette, IN 47907

I’m a Ph.D. student in the Department of Computer Science at Purdue University, advised by Professor Tianyi Zhang. My research interests lie at the intersection of software engineering and artificial intelligence.

I focus on developing techniques and tools to improve LLMs for coding tasks, including enhancing their capabilities and enabling more reliable, fine-grained evaluation.

In addition, I work on building knowledge graphs for software supply chain security and analyzing software dependencies to better understand their structure, risks, and impact.

news

Aug 21, 2026 Our paper on benchmarking LLM-based software supply chain vulnerability assessment has been accepted to the EMNLP 2026 Main Conference!
Jun 18, 2026 Our paper on conditional dependencies and their security impact in C/C++ has been accepted to ASE 2026!
Apr 06, 2026 Our paper on multi-agent web navigation has been accepted to the ACL 2026 Main Conference!
Aug 28, 2025 SecureChain has been selected for NSF’s National AI Research Resource (NAIRR) Pilot! NSF news, Purdue news.
Oct 31, 2024 Our paper on bidirectional grounding of LLM-based code generation has been accepted to the first round of ICSE 2025!

publications

  1. EMNLP
    VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities
    Jiahao Shi, Edward Tsien, Yifeng Di, and 10 more authors
    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
    arXiv
  2. ASE
    When Dependencies Depend: A Large-Scale Study on Conditional Dependencies and Their Security Implications in C/C++
    Yifeng Di, Juewei Zhang, and Tianyi Zhang
    In 2026 41st IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026
  3. ACL
    Mango: Multi-Agent Web Navigation via Global-View Optimization
    Weixi Tong, Yifeng Di, and Tianyi Zhang
    In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026
    arXiv
  4. ICSE
    Enhancing Code Generation via Bidirectional Comment-Level Mutual Grounding
    Yifeng Di and Tianyi Zhang
    In Proceedings of the IEEE/ACM 47th International Conference on Software Engineering, 2025
    arXiv Code
  5. ASE
    Software Entity Recognition with Noise-Robust Learning
    Tai Nguyen*, Yifeng Di*, Joohan Lee, and 2 more authors
    In 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023
    arXiv Code
  6. MSR
    SOSum: A Dataset of Stack Overflow Post Summaries
    Bonan Kou, Yifeng Di, Muhao Chen, and 1 more author
    In Proceedings of the 19th International Conference on Mining Software Repositories, 2022

preprints

  1. arXiv
    TRACER: A Semantic-Aware Framework for Fine-Grained Contamination Detection in Code LLMs
    Yifeng Di, Xuliang Huang, and Tianyi Zhang
    arXiv preprint arXiv:2605.24079, 2026
    arXiv