Chengyue Liu

About

I am a Ph.D. candidate in Computer Science at Nanyang Technological University, Singapore, advised by Prof. Yang Liu. Having passed my qualifying examination, I am now working toward my dissertation.

Before my Ph.D., I worked as an Algorithm Engineer at Shanghai TanXun Technology (Scantist) and as a Software Engineer / Project Manager at AVIC Airborne Systems Generic Technology Co., Ltd., where I contributed to the development of the C919, China’s first large commercial aircraft.

Research Interests

My research centers on AI for Software Engineering, with a focus on software supply-chain security, including software composition analysis (SCA) and vulnerability detection.

I also explore AI-agent frameworks and their applications: I applied AI agents to binary SCA (ISSTA 2026, ACM SIGSOFT Distinguished Paper Award), and built Xept, an AI agent for academic writing and a step toward the broader vision of AI Scientists, now serving 2,000+ users.

News

Sep 17, 2026

🏆 Our ISSTA 2026 paper “Beyond Similarity Scores: Evidence-Based Third-Party Library Detection for C/C++ Binaries” received the ACM SIGSOFT Distinguished Paper Award.

Jul 2026

Our paper “How Effective Are NPM Malicious Package Detectors? A Large-Scale Empirical Study” is accepted by ASE 2026.

Jun 25, 2026

Our paper “Mind the Gap: An Empirical Study of Synchronization Gaps, Delays, and Missed Opportunities in Software Forks” is accepted by ISSTA 2026.

Jun 11, 2026

Our paper “From Similarity Ranking to Definitive Verdict: LLM-Enhanced Source-to-Binary Function Localization” is accepted by OOPSLA 2026.

Apr 2026

Our paper “Beyond Similarity Scores: Evidence-Based Third-Party Library Detection for C/C++ Binaries” is accepted by ISSTA 2026.

Mar 2026

Our paper “Understanding the Limitations of C/C++ Binary Third-Party Library Detection Tools: An Empirical Study at Scale” is accepted by FSE 2026.

Publications

2026 5 papers

Understanding the Limitations of C/C++ Binary Third-Party Library Detection Tools: An Empirical Study at Scale

Chengyue Liu, Zhengzi Xu, Kaixuan Li, Jiahui Wu, Sihao Qiu, Siyuan Li, Siyang Xiong, Yang Xiao, Yang Liu

FSE 2026 CCF-A CORE A* First author PDF →

Beyond Similarity Scores: Evidence-Based Third-Party Library Detection for C/C++ Binaries

Chengyue Liu, Zhengzi Xu, Lyuye Zhang, Jiahui Wu, Kaixuan Li, Yang Liu

ISSTA 2026 CCF-A CORE A* First author 🏆 ACM SIGSOFT Distinguished Paper Award PDF →

From Similarity Ranking to Definitive Verdict: LLM-Enhanced Source-to-Binary Function Localization

Jingyi Shi*, Chengyue Liu*, Zhengzi Xu, Yang Xiao, Xingchu Chen, Yeting Li, Wei Huo, Yang Liu

OOPSLA 2026 CCF-A CORE A* Co-first author PDF →

Mind the Gap: An Empirical Study of Synchronization Gaps, Delays, and Missed Opportunities in Software Forks

Jiaying Zhu, Lyuye Zhang, Jiahui Wu, Chengyue Liu, Yang Liu

ISSTA 2026 CCF-A CORE A* Co-author PDF →

How Effective Are NPM Malicious Package Detectors? A Large-Scale Empirical Study

Wenbo Guo, Zhongwen Chen, Zhengzi Xu, Chengwei Liu, Ming Kang, Shiwen Song, Chengyue Liu, Yijia Xu, Weisong Sun, Yang Liu

ASE 2026 CCF-A CORE A* Co-author PDF →

2025 2 papers

BinStruct: Binary Structure Recovery Combining Static Analysis and Semantics

Yiran Zhang, Zhengzi Xu, Zhe Lang, Chengyue Liu, Yuqiang Sun, Wenbo Guo, Chengwei Liu, Weisong Sun, Yang Liu

ASE 2025 CCF-A CORE A* Co-author PDF →

Drop the Golden Apples: Identifying Third-Party Reuse by DB-Less Software Composition Analysis

Lyuye Zhang, Chengwei Liu, Jiahui Wu, Shiyang Zhang, Chengyue Liu, Zhengzi Xu, Sen Chen, Yang Liu

FSE 2025 CCF-A CORE A* Co-author PDF →

2023 1 paper

Ossfp: Precise and Scalable C/C++ Third-Party Library Detection Using Fingerprinting Functions

Jiahui Wu, Zhengzi Xu, Wei Tang, Lyuye Zhang, Yueming Wu, Chengyue Liu, Kairan Sun, Lida Zhao, Yang Liu

ICSE 2023 CCF-A CORE A* Co-author PDF →

Selected Projects

Xept — Academic Writing AI-Agent

An AI-native academic-writing platform I founded and lead, pairing LLM agents with real-time collaborative LaTeX editing. It now serves 2,000+ users on a paid-subscription model, with multi-agent workflows spanning the full paper lifecycle: literature search, outlining, drafting, data analysis, and revision.

xept.online →

Binary Software Composition Analysis

A research line on binary SCA that detects third-party libraries and known vulnerabilities directly in compiled C/C++ binaries. It powers BLADE, an evidence-based detection framework integrated into a commercial SCA product for compliance checks in regulated industries such as automotive.

Work Experience

2022 – 2024

Shanghai TanXun Technology (Scantist)

Algorithm Engineer

Designed and implemented the core algorithms of the company's binary SCA tool, deployed at multiple enterprises including CATARC (China Automotive Technology & Research Center) and Bank of China.