Junkai Chen

πŸ€— I am Junkai Chen (ι™ˆδΏŠε‡―), a Ph.D. student at Singapore Management University, advised by πŸ‘¨β€πŸ« Prof. David Lo. I received my master’s degree at Zhejiang University, where I was very fortunate πŸ’— to be advised by Prof. ✨ Xing Hu and Prof. 🌟 Xin Xia.

So many exciting and interesting (≧▽≦)/ things are happening in the era of AI (especially Large Language Models)!, where code seems to be a promising path from uninterpretable output to grounded actions. I am thrilled to be part of this time, and hope to make meaningful contributions to real world problems, with my research at the intersection of Software Engineering and Artificial Intelligence.

πŸ›« Reach out to me if you are interested!

News

  • [26/9/25] πŸ˜† Check our lastest preprint for evaluating πŸ” secure vide coding of code agents! We surprisingly find that, given the historical context of vulnerability introduction, current code agents still fall into human failures, even inducing other security issue!

  • πŸ€— Feel free to check and contribute recent SE conference papers at SEConfPaperList 〰️

Publications

Other Publications - [ICSE\'26 (NIER)] [**PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing**](https://arxiv.org/abs/2601.06910) \ Huihui Huang, Jieke Shi, **Junkai Chen**, Ting Zhang, Yikun Li, Chengran Yang, Eng Lieh Ouh, Lwin Khin Shar, and David Lo.
More TLDR: Pentesting with on-the-fly expert agents.
πŸ“„ PDF | πŸ’» Code
- [ICSE\'26] [**Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?**](https://arxiv.org/abs/2507.21817) \ Yikun Li, Ngoc Tan Bui, Ting Zhang, Chengran Yang, Xin Zhou, Martin Weyssow, Jinfeng Jiang, **Junkai Chen**, Huihui Huang, Huu Hung Nguyen, Chiok Yew Ho, Jie Tan, Ruiyin Li, Yide Yin, Han Wei Ang, Frank Liauw, Eng Lieh Ouh, Lwin Khin Shar, and David Lo.
More TLDR: New vulnerability datasets: TitanVul and BenchVul.
πŸ“„ PDF | πŸ’» Code
- [Preprint] [**Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework**](https://arxiv.org/abs/2510.01002) \ Chengran Yang, Ting Zhang, Jinfeng Jiang, Xin Zhou, Haoye Tian, Mingzhe Du, Jieke Shi, **Junkai Chen**, Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, and David Lo.
More TLDR: Vulnerability repair with code semantic-based RL.
πŸ“„ PDF
- [Preprint] [**R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation**](https://arxiv.org/abs/2504.04699)\ Martin Weyssow, Chengran Yang, **Junkai Chen**, Ratnadira Widyasari, Ting Zhang, Huihui Huang, Huu Hung Nguyen, Yan Naing Tun, Tan Bui, Yikun Li, Ang Han Wei, Frank Liauw, Eng Lieh Ouh, Lwin Khin Shar, and David Lo.
More TLDR: Reasoning for vulnerability detection.
πŸ“„ PDF | πŸ’» Code

\

* denotes equal contribution.

Awards

  • ACM SIGSOFT Distinguished Paper Award., ACM SIGSOFT, 2024
  • National Scholarship, Ministry of Education of P.R.C., 2024
  • SMU SCIS Research Excellence Award, SMU, 2025
  • ACM SIGSOFT CAPS Travel Grant, 2025

Services

Program Committee / Journal Reviewer

  • 2026: TOSEM, IST, ICSE (Shadow PC), MSR (Junior PC), DL4C@NeurIPS, EASE (AI Models / Data Track)
  • 2025: MSR (Junior PC), DL4C@ICLR, LTB@ICPE

Others

  • External Reviewer: ICSE, FSE, ASE, TOSEM, MSR, FCS, JSS (Chinese), etc.
  • Student Volunteer: Internetware 2023