Find Academic Supervisors

Shin YooView profile

Professor

• Software Testing
• Debugging
• Search-based Software Engineering
• +7 more

Shin Yoo is a tenured Full Professor in the School of Computing at Korea Advanced Institute of Science and Technology (KAIST), where he leads the Computational Intelligence for Software Engineering (COINSE) research group. He received his PhD from King's College London in 2009 under the supervision of Prof. Mark Harman. Currently, he serves as the General Chair for ASE 2025, which will be held in Seoul, Korea. Professor Yoo earned his PhD in Computer Science from King's College London (2009), following an MSc in Software Engineering with Distinction from the same institution (2006). His academic journey includes positions as Tenured Associate Professor (2021-2025), Associate Professor (2018-2021), and Assistant Professor (2015-2018) at KAIST, as well as Lecturer and Research Associate positions at University College London and King's College London. His research focuses on the intersection of software engineering and artificial intelligence, particularly in search-based software engineering, software testing, automated debugging, SE4AI (Software Engineering for AI), and AI4SE (AI for Software Engineering). Professor Yoo's work bridges theoretical foundations with practical applications, developing innovative techniques for fault localization, test case generation, and debugging using machine learning and genetic programming approaches. His research has significant implications for improving software reliability and development efficiency in both traditional software systems and AI-powered applications. Professor Yoo's recent publications demonstrate a clear trend toward leveraging large language models and deep learning techniques for software engineering tasks. His work spans fault localization, automated debugging, GUI testing, and program analysis, with increasing focus on the challenges and opportunities presented by AI systems. His research shows a consistent evolution from traditional search-based software engineering to AI/ML-enhanced approaches, reflecting the broader trends in the field. ACM SIGEVO HUMIES Silver Medal (2017) for human competitive application of genetic programming to fault localization research IEEE TCSE Most Influential Paper Award (ICST 2024) for work on mutation-based fault localization Professor Yoo has supervised five PhD students to completion, with his former students now holding positions as assistant professors, post-doctoral researchers, and software engineers at institutions including Kyoungpook National University, Max-Planck Institute Security & Privacy, Università della Svizzera Italiana, Roku Korea, and NUS. He currently serves as an associate editor for the Journal of Empirical Software Engineering and ACM Transactions on Software Engineering and Methodology, and has held significant leadership roles in major software engineering conferences including Program Co-chair for SSBSE (2014), ICST (2018), and ICSE NIER track (2020), General Chair for SSBSE (2022), and Testing & Analysis Area Chair for ICSE (2024). As leader of the Computational Intelligence for Software Engineering (COINSE) group at KAIST, Professor Yoo directs research that combines computational intelligence techniques with software engineering challenges. The group focuses on developing novel approaches to software testing, debugging, and analysis using search-based and AI-driven methods. Their work spans both theoretical foundations and practical implementations, with strong connections to industry challenges and applications.

Zhongxin LiuView profile

Assistant Professor

• Intelligent Software Engineering (AI4SE)
• Code Intelligence
• Vulnerability Detection
• +5 more

Zhongxin Liu is an Assistant Professor at the College of Computer Science and Technology , Zhejiang University , China. He earned his Ph.D. from the same institution in 2021. His research focuses on Intelligent Software Engineering (AI4SE) , leveraging software "big data" to improve code understanding, generation, and security through machine learning techniques. Published in top-tier venues: TSE, TOSEM, ICSE, FSE, ASE, ISSTA Active in academic service: Reviewer for TSE, TOSEM, ASEJ, etc. Visiting Professor at University of Stuttgart (2024-2025) His recent work explores Large Language Models (LLMs) for code intelligence, security hardening, and vulnerability detection. Papers emphasize cross-domain applications, zero-shot learning, and API/code dependency analysis. Scientific awards include: ACM SIGSOFT Distinguished Paper Awards (ASE 2018, 2019, 2020; ISSTA 2025) Zhejiang University Qizhen Scholar (2021) CCF TCSE Doctoral Dissertation Award (2023) Recruiting undergraduate interns, graduate students (MS/Ph.D.), and postdocs for code intelligence research. Contact: liu_zx@zju.edu.cn .

David LoView profile

Professor

• AI for Software Engineering
• Mining Software Repositories
• Data Mining
• +4 more

David Lo is the OUB Chair Professor of Computer Science and the founding Director of the Center for Research in Intelligent Software Engineering (RISE) at Singapore Management University. He has held significant leadership roles including General Chair of MSR'22 and ASE'16, and Program Committee Co-Chair for ASE'20, FSE'24, and ICSE'25. Lo has championed the field of AI for Software Engineering (AI4SE) since the mid-2000s, demonstrating how data mining, machine learning, information retrieval, natural language processing, and search-based algorithms can transform software engineering data into actionable insights and automation. His research spans Mining Software Repositories (MSR), large language models for code, software testing, smart contract analysis, and developer tooling. His recent publications reveal a strong focus on the intersection of large language models and software engineering, with particular attention to code generation, evaluation, documentation, and the practical implications of AI tools for developers. His work increasingly addresses economic efficiency, privacy concerns, and human factors in AI-assisted development. Two Test-of-Time awards Eleven ACM SIGSOFT/IEEE TCSE Distinguished Paper awards ACM Fellow IEEE Fellow ASE Fellow National Research Foundation Investigator (Senior Fellow) Lo has supervised numerous students and collaborated extensively across the software engineering community. His work on Mining Software Repositories has led to practical tools and insights that have shaped the field. He regularly contributes to major conferences and has served in leadership roles across ASE, ICSE, and FSE communities. As founding Director of the Center for Research in Intelligent Software Engineering (RISE) at SMU, Lo leads a research group focused on advancing AI techniques for software engineering problems, with emphasis on practical applications that address real developer pain points.

Gregory GayView profile

Associate Professor

• Software Testing
• Search-Based Software Engineering
• AI for Software Engineering
• +4 more

Gregory Gay is an Associate Professor in the Interaction Design and Software Engineering division within the Department of Computer Science and Engineering at Chalmers University of Technology and the University of Gothenburg, Sweden. His academic profile spans numerous software engineering conferences where he has served as committee member, program chair, and active researcher since at least 2018. Dr. Gay's research focuses on the intersection of software engineering and artificial intelligence, with particular emphasis on: Software Testing and Analysis Search-Based Software Engineering AI for Software Engineering (AI4SE) AI Engineering Automation of development tasks Software Carbon Footprint and sustainability His recent publications demonstrate a strong trend toward applying AI and optimization techniques to software testing challenges, with increasing focus on sustainability aspects of software development. Many studies take an industrial perspective, examining real-world applications in automotive software systems. His work blends theoretical foundations with practical applications, making significant contributions to both academic research and industrial practice in software engineering. Dr. Gay has been actively involved in numerous top software engineering conferences including ASE, ICSE, ESEC/FSE, ISSTA, and ICST, serving on program committees and organizing tracks. His research methodology typically combines optimization, artificial intelligence, and machine learning to help developers deliver complex systems in a safe, secure, and efficient manner.

Wenchao GuView profile

Research Fellow

• Artificial Intelligence
• Software Engineering
• Computational Linguistics
• +5 more

Dr. Wenchao GU is a Postdoctoral Researcher at the Chair of Software Engineering & AI at the Technical University of Munich (TUM) , working under the supervision of Prof. Chunyang Chen. His academic journey includes a PhD in Computer Science and Engineering from The Chinese University of Hong Kong (CUHK) (2024), an MSc in Information Science from Tohoku University (2017), and a B.Eng in Mechanical and Aerospace Engineering from Tohoku University (2015). Research Interests: Dr. GU's work focuses on Artificial Intelligence for Software Engineering (AI4SE) , leveraging Large Language Models (LLMs) to advance source code understanding, analysis, and generation. Key areas include code optimization , vulnerability detection , and UI code generation . His research bridges theoretical innovations with practical tools for automated code efficiency improvement, semantic code retrieval, and natural language generation in software development workflows. Publication Trends : His recent work emphasizes iterative LLM refinement via evolutionary search (2025), segmented deep hashing for scalable code retrieval (2025), and contrastive learning in code search (2023). Earlier studies explored AST-guided transformers for code summarization (2022) and semantic dependency learning in code retrieval (2021). Scientific Awards: Distinguished Paper Award, ICSE 2025 The Aoba Foundation Scholarship (2015) JASSO Scholarship (2012) Tohoku University President Fellowship (2012) Mentorship: Dr. GU supervises 11 current students (including 1 PhD) and has advised 5 graduated Master's students. He actively seeks candidates with web/Android development expertise for UI code generation projects.

Ying ZouView profile

Professor

• Software Engineering
• Artificial Intelligence for Software Engineering
• Software Evolution
• +2 more

Dr. Ying Zou is a Professor in the Department of Electrical and Computer Engineering at Queen's University's Smith Engineering faculty in Kingston, Ontario, Canada. With an extensive publication record spanning from 2018 through 2025, Dr. Zou has established herself as a leading researcher in empirical software engineering with a growing focus on AI integration. Dr. Zou's research focuses on Software Engineering , Artificial Intelligence for Software Engineering (AI4SE) , Software Evolution , Software Analytics , and Empirical Software Engineering . Her work bridges theoretical approaches with practical applications, examining developer behavior, code quality improvement, and AI techniques for software engineering tasks. Recent publications demonstrate a clear progression from traditional empirical studies toward more AI-centric approaches, particularly in code refactoring, type inference, and performance analysis. Analysis of Dr. Zou's publication trends reveals a strategic evolution in her research focus. Early work centered on empirical studies of Stack Overflow and GitHub, while recent publications increasingly integrate large language models and AI techniques for software engineering tasks. Her research spans multiple dimensions including code quality, developer productivity, open source community dynamics, and performance optimization, with consistent methodological rigor in empirical validation. Dr. Zou has served in numerous leadership roles across major software engineering conferences including ASE, ICSE, and ESEC/FSE. She has been a Program Committee member for multiple tracks and conferences, and notably served as New Faculty Mentoring Co-Chair for ESEC/FSE 2026. Her service to the community extends to organizing conference tracks, chairing sessions, and mentoring new researchers in the field.

Mingwei LiuView profile

Associate Professor

• Software Engineering
• Artificial Intelligence
• AI4SE
• +4 more

Dr. Mingwei Liu is an Associate Professor at the School of Software Engineering, Sun Yat-Sen University, China. Previously, he completed postdoctoral research at Fudan University in 2024 and received both his Ph.D. (2022) and B.E. (2017) in Software Engineering from Fudan University under the mentorship of Xin Peng. Dr. Liu's research focuses on the intersection of Software Engineering (SE) and Artificial Intelligence (AI), specifically in the domains of AI4SE (AI for Software Engineering) and SE4AI (Software Engineering for AI). His primary interest lies in leveraging advanced AI technologies, particularly large language models (LLMs) and knowledge graphs (KGs), to address complex software engineering challenges and tackle system engineering problems in AI applications. His research portfolio demonstrates a strong focus on practical applications of AI in software development, with particular emphasis on code generation, vulnerability detection, test generation, and knowledge representation for software artifacts. Through his work, Dr. Liu has contributed significantly to understanding how LLMs perform in realistic software development scenarios beyond simple function-level code generation. Dr. Liu has published over twenty papers in top international journals and conferences including TSE, TOSEM, ICSE, FSE, and ASE. His research has been recognized with prestigious awards including the IEEE TCSE Distinguished Paper Award (ICSME 2018) and the ACM SIGSOFT Distinguished Paper Award (FSE 2023). IEEE TCSE Distinguished Paper Award (ICSME 2018) ACM SIGSOFT Distinguished Paper Award (FSE 2023) Dr. Liu actively contributes to the academic community as a program committee member for major conferences including ASE, ESEC/FSE, ICSME, and SANER. He leads the SYSUSELab research group, which has developed notable resources including the ClassEval benchmark for evaluating LLMs on class-level code generation tasks.

Vahid AlizadehView profile

Assistant Professor

• Empirical Software Engineering
• Software Quality
• Software Refactoring & Maintenance
• +7 more

Vahid Alizadeh is an Assistant Professor in the College of Computing and Digital Media (CDM) at DePaul University in Chicago, USA, where he has been serving since 2020. His academic career focuses on bridging the gap between software quality research and industrial practice through empirical studies and intelligent tool development. Education: Ph.D. in Computer Science, University of Michigan (2015-2020) M.Sc. in Electrical Engineering, University of Tehran (2011-2013) B.Sc. in Electrical Engineering, Iran University of Science and Technology (2006-2011) Research Interests: Dr. Alizadeh's research spans empirical software engineering, software quality, refactoring & maintenance, intelligent software engineering, and AI-enabled systems. His work combines rigorous empirical methods with practical tool development to address real-world software engineering challenges. He has particular expertise in developing intelligent refactoring technologies that are currently deployed by organizations impacting thousands of programmers worldwide. Research Trends: His publication record shows a consistent focus on applying AI and machine learning techniques to software engineering problems, particularly in the areas of refactoring and quality assurance. Recent work demonstrates increasing integration of AI/ML approaches with traditional software engineering practices, reflecting the broader trend toward AI4SE (AI for Software Engineering). Awards & Recognition: Excellence in Teaching Award from DePaul University (2025) $67,000 DePaul-RFUMS Grant for AI-Powered Community Pharmacy Research (2024) ACM SIGSOFT Distinguished Paper Award at MODELS Conference (2020) Distinguished University of Michigan-Dearborn Honors Scholar (2020) Outstanding Graduate Research Assistant Award (2018/2019) Professional Activities: Dr. Alizadeh has served in various capacities at major software engineering conferences including ASE 2022 as Session Chair and Virtualization Co-Chair, and MODELS 2025 as Web Co-Chair. His work has resulted in one patent and multiple invention licenses through the University of Michigan Tech Transfer Office. He actively mentors graduate students interested in empirical software engineering, software quality, and intelligent refactoring technologies.

Dong WangView profile

Associate Professor

• Empirical Software Engineering
• Mining Software Repositories
• AI4SE

Dong Wang is an Associate Professor at Tianjin University, China, specializing in software engineering research with a focus on empirical methods and AI applications in software development. His primary research interests include: Empirical Software Engineering Mining Software Repositories AI for Software Engineering (AI4SE) Professor Wang has established himself as a significant contributor to the software engineering research community through numerous publications at top conferences. His work spans software testing, programming tools, developer productivity, and open source software development, with particular emphasis on applying AI techniques to software engineering problems. His recent publications demonstrate expertise in unit test generation, JVM fuzzing, equivalent mutant detection, and studies of developer tools like GitHub Copilot. His contributions have been recognized through publications at premier software engineering venues including ASE, ICSE, FSE, and ICSME across multiple years from 2023-2025. Professor Wang is actively engaged in the research community, serving on program committees for numerous conferences and participating in New Ideas and Emerging Results tracks, demonstrating his commitment to advancing the field and supporting emerging research directions.

DongGyun HanView profile

Assistant Professor

• Software Engineering
• Code Review
• Empirical Study
• +2 more

DongGyun Han is a Lecturer (equivalent to Assistant Professor) in the Department of Computer Science at Royal Holloway, University of London. His research specializes in Software Engineering, with emphases on Empirical Study, AI for Software Engineering (AI4SE), Software Engineering for AI (SE4AI), and Code Review. He holds a PhD from University College London (UCL), an MPhil from Hong Kong University of Science and Technology (HKUST), and a B.Eng from Jeju National University. Dr. Han's research integrates empirical methods with AI techniques to address challenges in software maintenance, code quality, and developer productivity. His work spans automated code review, defect prediction, vulnerability repair, and AI model applications in software artifacts. He actively collaborates with industry partners including Amazon Web Services. His recent publications focus on leveraging large language models for software tasks, analyzing dataset biases, and improving automated developer tools. Common themes include empirical validation of AI techniques, security enhancement, and optimizing developer workflows. Awards: No scientific awards mentioned in source materials. Academic Service: Dr. Han contributes extensively to program committees for top-tier conferences including ICSE, FSE, ASE, and MSR. He has chaired tracks at ICTSS 2024 and reviewed for journals including TOSEM, EMSE, and JSS. Affiliations: Previously affiliated with Singapore Management University's SOftware Analytics Research (SOAR) group and Secure Mobile Centre. Maintains industry connections through past roles at Amazon Web Services.

Valerio TerragniView profile

Senior Lecturer

• Software Engineering
• Software Testing
• Test and Oracle generation
• +5 more

Valerio Terragni is a Senior Lecturer in the Department of Electrical, Computer, and Software Engineering at the University of Auckland, New Zealand, where he also serves as the Program Director of the Software Engineering Degree. His position as Senior Lecturer in New Zealand is equivalent to Associate Professor in many Asian, European, and North American academic systems. His educational background includes a PhD in Computer Science from The Hong Kong University of Science and Technology (2017), and B.Sc. and M.Sc. degrees in Computer Science from the University of Milano-Bicocca, Italy. Prior to his current position, he was a Senior Research Fellow at Università della Svizzera italiana (USI) in Lugano, Switzerland from 2017 to 2020. Dr. Terragni's research focuses primarily on Software Testing, with special emphasis on automated techniques for generating test cases and their applications in modern software systems. His current work centers on SE4AI (Software Engineering for AI) and AI4SE (AI for Software Engineering), particularly investigating the intersection of software testing and large language models. His research has been published in leading software engineering venues including IEEE TSE, ACM TOSEM, ICSE, FSE, ASE, ICST, and ISSTA. His recent publications demonstrate a strong focus on metamorphic testing, particularly for AI systems and large language models, as well as work on test oracle generation, software quality assessment, and software engineering education. His research shows a clear evolution from traditional software testing techniques toward addressing the unique challenges posed by AI systems. As Program Director of the Software Engineering Degree at the University of Auckland, Dr. Terragni plays a significant role in shaping software engineering education. His work on GradeStyle demonstrates his commitment to improving programming education through automated assessment tools integrated with GitHub.

Maliheh IzadiView profile

Assistant Professor

• Software Engineering
• Machine Learning
• Large Language Models for Code
• +7 more

Maliheh Izadi is a tenure-track assistant professor in the Faculty of Electrical Engineering, Mathematics, and Computer Science at Delft University of Technology (TU Delft), Netherlands. She leads the AISE (AI-enabled Software Engineering) research lab and serves as the scientific manager for the TU Delft/JetBrains Collaboration (AI4SE). She is also a member of the Software Engineering Research Group (SERG) at TU Delft and actively supervises PhD, MSc, and BSc students. Dr. Izadi's research focuses on enhancing software development tools through building smarter software and tailoring machine learning and NLP techniques to source code. Her primary interests include building and tailoring large language models (LLMs) and autonomous agents to source code, with specific focus areas including evaluation, benchmarking, model memorization, IDE integration, in-IDE Human-AI interaction, and extending models' capabilities to low-resource programming languages. Her work bridges the gap between deep learning and source code analysis, with applications in code understanding, generation, documentation, and developer productivity enhancement. Her recent publications reveal a strong trend toward evaluating and improving LLMs for code, with emphasis on safety, usability, and efficiency. She has made significant contributions to benchmark development, harmfulness assessment of LLMs in programming contexts, and improving the integration of AI tools within development environments. Her research consistently addresses real-world industrial challenges while advancing theoretical understanding of model behavior. Google Research Scholar Award (2025) for proposal on Tackling LLM Hallucinations Amazon Research Award (2024) for proposal on Addressing Memorization in Code LLMs ACM SIGSOFT Distinguished Paper Award (2025) for How Much Do Code Language Models Remember? ACM SIGSOFT Distinguished Paper Award (2024) for A Transformer-Based Approach for Smart Invocation of Automatic Code Completion Best Tool Award at SaTML'22 competition for STACC Best Tool Award at NLBSE'22 competition for Catiss Dr. Izadi actively collaborates with industry partners, particularly JetBrains Research, where she leads the AI4SE ICAI lab. She has supervised multiple PhD and master's students and has served on program committees for major software engineering conferences including ASE, ICSE, FSE, and MSR. Her research has been published in top venues such as IEEE/ACM ICSE, FSE, ASE, TOSEM, EMSE, MSR, ICSME, SANER, and JSS. She is also organizing the First International workshop on Autonomous Agents in Software Engineering (AgenticSE) co-located with ASE'25.

Fatemeh Hendijani FardView profile

Assistant Professor

• Code Intelligence
• Transfer Learning
• AI4SE
• +5 more

Fatemeh Hendijani Fard is an Assistant Professor in the Department of Computer Science at the University of British Columbia's Okanagan campus. She serves as a graduate student supervisor and teaches courses in Computer Science and Data Science. Dr. Fard is a member of the CITECH program and MMRI, part of the Killam family of scholars, and an active member of both IEEE and ACM. Her research focuses on the intersection of Natural Language Processing and Software Engineering, with particular emphasis on developing code intelligence models for low-resource programming languages like R. She conducts empirical studies and develops techniques to improve the computational efficiency of code-language models while making them accessible to communities with restricted GPU access. Her work strongly advocates for Diversity and Inclusion in STEM, particularly for underrepresented females. Analysis of Dr. Fard's recent publications reveals a strong research trajectory in adapting Large Language Models for code intelligence with a focus on efficiency and accessibility. Her work spans multiple dimensions including code summarization, method name prediction, code search, code clone detection, and program repair, with special attention to low-resource programming languages. A notable trend is her exploration of adapter-based approaches for knowledge transfer that reduce computational requirements while maintaining performance. Izaak Walton Killam Memorial Scholarship Alberta Innovates Technology Futures (AITF) NSERC Discovery NSERC CREATE Mitacs Accelerate UBC Start-up Fund Dr. Fard has secured significant research funding including NSERC Discovery, NSERC CREATE, Mitacs Accelerate, and UBC Start-up funds to support her work on code intelligence for low-resource programming languages. She actively serves as a graduate student supervisor, guiding research in areas related to code representation learning and mining software repositories. Her service to the academic community is extensive, having served on program committees for major conferences including FSE, MSR, ASE, SANER, and ICSME across multiple years. Dr. Fard leads research initiatives focused on making code intelligence accessible to communities working with understudied programming languages. Her team conducts empirical studies and develops new techniques specifically designed for low-resource languages, with particular attention to the R programming language. This work addresses diversity and inclusion in AI tools by ensuring developers with limited computational resources can benefit from advances in neural networks and automated tools.

Zhou YangView profile

Assistant Professor

• Software Engineering
• Artificial Intelligence
• AI for Software Engineering
• +3 more

Zhou Yang is an Assistant Professor at the University of Alberta and Fellow at the Alberta Machine Intelligence Institute (Amii), with research focusing on the intersection of software engineering and artificial intelligence. His academic journey includes a Ph.D. from Singapore Management University, an M.Sc. in Software System Engineering from University College London, and undergraduate studies at Yangzhou University. His research interests span Software Engineering, Artificial Intelligence, AI for Software Engineering (AI4SE), Software Engineering for AI (SE4AI), Large Language Models, and Cybersecurity. Yang's work explores how human and AI collaboration can improve code writing, how AI impacts open-source communities, and how developers build software in emerging environments like VR/AR. His recent publications demonstrate strong trends in code language models, with significant contributions to ASE, ICSE, ISSTA, and top journals like TOSEM and TSE. His research addresses critical challenges including token efficiency in code generation, user perception of AI coding assistants, privacy preservation in code models, and fairness in AI systems. 2024 IEEE Computer Society Best Paper Award (1 out of 183 submissions) ACM Distinguished Paper Award from ISSTA 2024 Distinguished Reviewer Award from Internetware 2024 SMU Research Staff Excellence Award (1 of 4 university-wide) SMU Presidential Fellowship Award SMU Dean's List Award 1st Place in ACM Student Research Competition at ICSE 2024 Yang actively mentors graduate students with regular one-on-one meetings, constructive feedback, and support for top-venue publications. He provides full funding through teaching assistantships and research grants, including travel support for conferences. His lab focuses on responsible research conduct and societal implications of AI work. Though early-career, he actively builds professional networks for students through collaborations and supports diverse career paths in academia and industry. He leads research in the Alberta Machine Intelligence Institute, focusing on practical applications where software engineering principles enhance AI systems and where AI techniques solve real-world software engineering challenges.

Zhongxin LiuView profile

Assistant Professor

• Intelligent Software Engineering
• AI for Software Engineering
• Code Intelligence
• +5 more

Zhongxin Liu is a Distinguished Research Fellow (Assistant Professor) and Doctoral Supervisor at the College of Computer Science and Technology, Zhejiang University. He received his Ph.D. from Zhejiang University under the supervision of Prof. Shanping Li. His research focuses on intelligent software engineering (AI4SE), particularly using AI to help developers understand, write, change, and test code through learning from software "big data". His educational background includes: Ph.D. in Computer Science, Zhejiang University (2016-2021) Dr. Liu's research interests center around intelligent software engineering with emphasis on code intelligence, program analysis, and software testing. His work leverages machine learning, particularly large language models, to solve challenging problems in software development including code generation, bug localization, and test case generation. He has made significant methodological contributions to the field through his innovative approaches to understanding and improving the software development lifecycle. His recent publications (2024-2026) demonstrate a clear trend toward leveraging large language models for software engineering tasks, with particular focus on code generation, fault localization, and program analysis. The research spans multiple domains including vulnerability detection, smart contract development, and cross-domain code search, showing how AI can enhance traditional software engineering practices. Dr. Liu has received numerous prestigious awards for his contributions: ACM SIGSOFT Distinguished Paper Award (ISSTA 2025, ASE 2018-2020) Distinguished Paper Award (APSEC 2023) Zhejiang University Education Foundation Qizhen Scholar (2021) Distinguished Doctoral Thesis of Zhejiang University (2021) As a Doctoral Supervisor at Zhejiang University, Dr. Liu mentors graduate students in intelligent software engineering. He serves on program committees for major conferences including ICSE, ASE, and FSE. His research group actively recruits undergraduate interns, graduate students, and postdocs to work on code intelligence projects. Dr. Liu is also scheduled to be a Visiting Professor at the University of Stuttgart from October 2024 to January 2025. Dr. Liu leads a vibrant research group at Zhejiang University focused on advancing AI-powered tools for software development. His work bridges theoretical advances in machine learning with practical applications in software engineering, creating novel solutions that help developers be more productive and produce higher quality code.