Dr. Tao Zhang

Dr. Tao Zhang is a Full Professor at the School of Computer Science and Engineering, Macau University of Science and Technology (MUST), Macau SAR. He received his Ph.D. from the Department of Computer Science and Engineering at the University of Seoul. After that, he spent one year at the Hong Kong Polytechnic University as a Postdoctoral Research Fellow. He received his B.S. in Automation and M.Eng in Software Engineering from Northeastern University, China. Tao is a senior member of ACM and IEEE. He published more than 100 high-quality papers in renowned software engineering and security journals and conferences, such as ICSE, ESEC/FSE, ASE, TSE, TOSEM, EMSE, JSS, IST, TIFS, TDSC, and TSC. He serves/served as General or Program Chair of numerous academic conferences, including APSEC 2025, Internetware 2024, SANER 2023, and DSA 2021. He also serves as the PC member of several top-tier SE conferences, including ICSE, FSE, ASE, and ISSTA. He is currently an Associate Editor for IEEE Transactions on Software Engineering (TSE), IEEE Transactions on Reliability (TRel), and the Journal of Systems and Software (JSS). He is also an Editorial Board Member for Empirical Software Engineering (EMSE) and Science of Computer Programming (SCP).

Contact: tazhang@must.edu.mo

Web: https://cszhangtao.github.io/

Linkedin: https://www.linkedin.com/in/tao-zhang-25458229/

Abstracts

Frontiers in Intelligent Software Data Analytics

Intelligent Software Data Analytics has long been a focal research topic in software engineering. With the emergence of new AI technologies such as deep learning and large language models (LLMs), these intelligent analysis methods have demonstrated promising results in data analytics tasks across software development and testing processes. However, they also present significant challenges. Our research has evolved from traditional information retrieval and machine learning-based approaches to leveraging advanced techniques like deep learning and LLMs. We have proposed solutions for various software engineering and security challenges, including code search, defect localization, priority prediction, malware detection, and smart contract vulnerability detection, among others. Additionally, we have developed a suite of supporting tools. While these tools have achieved performance improvements in their respective tasks, they have also prompted deeper reflections, such as "Are large models truly a panacea?"—and provided valuable insights for our future work.

How AI is Changing the World of Software Engineering

With the rapid growth of AI, it deeply influences almost all of computer science, especially for software engineering. The software development process generates a large amount of corpus data (such as defect reports, source code, logs, etc.). How to use these corpus data to better implement automated software engineering tasks is a big challenge. The difficulty lies in the semantic gap between natural language and programming language. In this new era, generative AI can help automatically produce more reliable source code, patches, commits, code comments, and responses to user reviews by deeply analyzing the semantic relations between natural language and programming language. For achieving the best performance of automated software engineering tasks, a lot of software engineering scholars walk through a long road. For our team, we started from the initial reliance on bug reports or user review information to perform a single automated software engineering task. By establishing a unified neural network model and a unified representation model for bug reports, we constructed a set of methods that can achieve multiple automated software engineering tasks. In the process, we discovered the over-interpretation problem of pre-trained language models when implementing automated software engineering tasks, and proposed mitigation strategies. Following this way, depending on the huge power of LLMs, we proposed a series of new models and corresponding tools to enhance the performance of automated software engineering tasks.