AI + SE Seminar Series
The incredible advances in AI/ML (Artificial Intelligence/Machine Learning) over the last few years are enabling the development of AI-enabled software systems. The trustworthiness and quality assurance of such systems remains a difficult challenge. At the same time, foundational models like Large Language Models (LLMs) show that various software development tasks (e.g., coding) can now be supported with AI-based suggestions (e.g., intelligent code completions)
The AI+SE seminar series invites speakers from academia and industry who are working at the intersection of AI and SE (SE = Software Engineering), such as the design of AI-enabled systems, quality assurance and testing of AI/ML models and their operationalization into software systems, as well as the modernization of traditional software development practices and works with ML-based techniques.
Learn more about the AI + SE Seminar Series.
May 17: Software Quality Assurance in the Era of Large Language Models
In recent years, Large Language Models (LLMs), such as GPT-4 and Claude-3, have shown impressive performance in various downstream applications, including software engineering. In this talk, I will discuss the potential impact of modern LLMs on the important problem of software quality assurance, along with our recent research findings. I will first talk about the new opportunities and possibilities LLMs can offer for better quality assurance of real-world software systems. Next, I will talk about the new quality assurance challenges or issues raised by code LLMs themselves and deep learning in general, including strategies for mitigation. Lastly, I will also briefly discuss our recent experiences in building fully open-source code LLMs (such as StarCoder2 and Magicoder) for supporting better software quality assurance in the LLM era.
Bio
Lingming Zhang is an Associate Professor in the Department of Computer Science at the University of Illinois Urbana-Champaign (UIUC). His main research interests lie in Software Engineering and Programming Languages, as well as their synergy with Machine Learning, including Large Language Models for Code and ML System Reliability. To date, his work has found 1000+ new bugs/vulnerabilities in real-world software systems, including deep learning compilers/libraries, C/C++ compilers, Java virtual machines, operating systems, and even quantum computing systems. He is the recipient of ACM SIGSOFT Early Career Researcher Award, NSF CAREER Award, and UIUC Dean’s Award for Excellence in Research. Additionally, he has received multiple ACM SIGSOFT Distinguished Paper Awards and various awards/grants from leading tech companies such as Alibaba, Amazon, Google, Kwai Inc., Meta, NVIDIA, and Samsung. He currently serves as program co-chair for ASE 2025 and LLM4Code 2024, and associate chair for OOPSLA 2024.