General Information
Biography
Myoungkyu Song is an Associate Professor in the Department of Computer Science at the University of Nebraska at Omaha. Prior to joining UNO, he was a postdoctoral researcher at the Center for Advanced Research in Software Engineering (ARiSE) in the Department of Electrical and Computer Engineering at The University of Texas at Austin. He received his Ph.D. in Computer Science from Virginia Tech.Prior to entering academia, he held software engineering and research staff positions in industry, including roles at Samsung Electronics and LG Electronics.His research focuses on software engineering and program analysis, with an emphasis on AI- and large language model (LLM)-assisted software development, software correctness and security, and automated program understanding and transformation. His recent work explores how learning-based techniques can be combined with program analysis to improve software reliability, robustness, and developer productivity, particularly in educational and security-sensitive contexts.
Teaching Interests
Dr. Song’s teaching philosophy centers on bridging the gap between foundational software engineering theories and practical, real-world applications. He is committed to equipping students with the critical thinking skills and technical proficiency needed to build robust, secure, and maintainable software systems. In his courses, Dr. Song emphasizes the importance of understanding the entire software lifecycle—from design and implementation to evolution and quality assurance—often integrating modern tools and AI-assisted techniques to prepare students for the evolving landscape of the industry. His primary teaching interests include: (1) Software Engineering, covering fundamentals of software design, architecture, and development processes (SDLC); (2) Software Evolution and Maintenance, focusing on techniques for refactoring, legacy system analysis, and managing software changes; (3) Program Analysis and Testing, which involves automated debugging, static/dynamic analysis, and verification methods to ensure software correctness; and (4) Secure Software Development, emphasizing practices for identifying vulnerabilities and writing secure code.
Research Interests
Dr. Song’s research interests are broadly centered on software engineering and program analysis, with a sincere aspiration to improve the correctness, security, and maintainability of real-world software systems. He is interested in exploring how automated analysis and learning-based techniques can meaningfully support developers throughout the software lifecycle, ranging from program understanding and evolution to secure development and education.One of the primary areas he has dedicated his efforts to is program understanding and software evolution. Dr. Song has focused on developing techniques that analyze software changes, refactorings, and recurring modification patterns to aid in tasks such as code review and regression testing. Through this work, he aims to assist developers in reasoning about complex codebases by attempting to make software changes more transparent and interpretable.Another aspect of his research involves exploring automated support for software correctness and security. He is actively investigating methods to detect, explain, and potentially repair defects and insecure coding practices by combining static analysis with statistical methods and machine learning. This work aims to contribute to automated bug detection and the creation of tools that provide actionable, constructive feedback to developers.Recently, Dr. Song has expanded his research scope to include AI- and Large Language Model (LLM)-assisted software engineering. He examines how LLMs can be harmoniously integrated with traditional program analysis to facilitate tasks like code completion, summarization, and human–AI collaboration. He places particular emphasis on designing systems that leverage human expertise alongside learning-based models, aiming to enhance reliability and trustworthiness, especially within educational and security-sensitive contexts.He is also deeply committed to AI-assisted programming education. His work in this area explores how intelligent tutoring systems can guide students in learning secure and effective software development practices. By bridging software engineering, education, and AI, Dr. Song aims to support learning outcomes while reinforcing fundamental software engineering principles for the next generation of developers.
Education
Ph D, Virginia Tech, Blacksburg, VA, Computer Science, Software Engineering, 2013