I’m Chengran Yang, a fourth-year Ph.D. Candidate at the School of Computing and Information Systems (SCIS), Singapore Management University (SMU), working under the supervision of Professor David Lo (ACM & IEEE Fellow). My research lies at the intersection of Software Engineering (SE) and Artificial Intelligence (AI), focusing on Harnessing SE Community Knowledge for Developer-Centric Code Intelligence. My work targets two primary directions:

• (1) Improving Code Quality and Security in AI-driven Systems, specifically focusing on code correctness, runtime efficiency, and vulnerability detection;
• (2) Integrating Intelligent Assistants into Developer Workflows, enabling automated and intelligent support for developer activities, such as automated question answering, documentation generation, and structured code reasoning.

I have 14 publications in top-tier software engineering venues, e.g., ICSE, ASE, TSE, and TOSEM, and received the SMU Presidential Doctoral Fellowship. Before my doctoral studies, I earned my bachelor’s degree from the University of Electronic Science and Technology of China (UESTC) and interned at the Institute of Computing Technology, Chinese Academy of Sciences, under the supervision of Prof. Jianfeng Zhan.

News

• Jun. 2025 “Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning” got accepted by ICSE 2026
• Jun. 2025 “APIDocBooster: An Extract-Then-Abstract Framework Leveraging Large Language Models for Augmenting API Documentation” got accepted by ICSME 2025
• May. 2025 “R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation” ranked top-3 most liked papers in the Software Engineering category on the Alphaxiv platform.
• May. 2025 “ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models” got a major revision by TOSEM

Lead Contributions (Last 2 Years)

• Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning
  Chengran Yang, Zhensu Sun, Hong Jin Kang, Jieke Shi, David Lo
  ICSE 2026
• Apidocbooster: An extract-then-abstract framework leveraging large language models for augmenting api documentation
  Chengran Yang, Jiakun Liu, Bowen Xu, Christoph Treude, Yunbo Lyu, Junda He, Ming Li, David Lo
  ICSME 2025
• Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection
  Chengran Yang (co-first author), Ting Zhang, Yindu Su, Martin Weyssow, Hung Nguyen, Tan Bui, Hong Jin Kang, Yikun Li, Eng Lieh Ouh, Lwin Khin Shar, David Lo
  Under Submission
• ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
  Chengran Yang, Hong Jin Kang, Jieke Shi, David Lo
  TOSEM Major Revision
• R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
  Martin Weyssow, Chengran Yang, Junkai Chen, Yikun Li, Huihui Huang, Ratnadira Widyasari, Han Wei Ang, Frank Liauw, Eng Lieh Ouh, Lwin Khin Shar, David Lo
  Under Submission

Service

PC Member:

• MSR 2023 (junior PC)
• APSEC2023 (Student Research Competition)

Reviewer:

• Automated Software Engineering
• Neurocomputing
• TOSEM