Towards next-generation automated web development
29/8/2025, 3:00pm
Speaker
Abstract
Websites and web applications are vital in today’s digital landscape, but designing their visual elements, such as buttons, layouts, and interactive features, is often complex and time-consuming for developers. Although modern large language models (LLMs) show promise, they still struggle to fully interpret designs and convert them into functional web pages. This talk examines how advanced AI can help automate web development. I will summarize current uses of LLMs in web engineering, highlight key limitations and failure modes, and outline research directions and practical improvements to make AI-driven web creation more robust and effective.
Bio
Yintong Huo is an Assistant Professor at the School of Computing and Information Systems, Singapore Management University. She earned her Ph.D. from The Chinese University of Hong Kong. Her research spans software reliability, log analysis, and LLM-driven code generation, with more than 20 publications in software engineering venues. She has served on program committees for leading conferences, including ICSE, FSE, and ASE, and is a recipient of the IEEE Open Software Services Award and the ICSE Distinguished Reviewer Award.