Chunyang Chen

AI + SE Seminar Series (July 26, 9:30 EST).

Mobile Application Testing with Large Language Models: Landscape and Vision

Mobile apps are now indispensable for people’s daily life. To ensure the app quality, automated GUI testing is widely explored for locating bugs. However, there are many issues with current GUI testing tools including low activity coverage, excessive overhead, and missing issues of app usability (e.g., GUI aesthetics or animation) and accessibility (e.g., to the aged and disabled like the blind). The emergence of powerful Large Language Models (LLM) brings an opportunity to overcome these GUI testing issues. In this talk, he is going to introduce his latest works on different aspects of mobile app testing such as boosting GUI testing coverage, testing case generation, and automated visual bug replay, by leveraging LLM methods including GPT-3/4, and ChatGPT. In addition to the academic publications mentioned above, he will also share a landscape of existing works in using LLM in software testing and share the potential future directions in this field.

Bio

Dr Chunyang Chen is a full professor in the School of Computation, Information and Technology, Technical University of Munich, Germany. His main research interest lies in automated software engineering, especially data-driven mobile app development. Besides, he is also interested in Human-Computer Interaction and software security. He has published 100+ research papers in top venues such as ICSE, FSE, ASE, CHI, CSCW with extensive collaboration with industry, including Google, Microsoft, and Meta. His research has won awards including ACM SIGSOFT Early Career Researcher Award, Facebook Research Award, four ACM SIGSOFT Distinguished Paper Awards (ICSE’23/21/20, ASE’18), and multiple best paper/demo awards.

For more details, please visit: https://chunyang-chen.github.io/

EECS Upcoming Events: https://lassonde.yorku.ca/eecs/eecs-upcoming-events/

Video Recording: Here