In this talk, I will discuss the opportunities and challenges of software-AI synergy: (1) using software approaches such as software testing to improve the reliability of deep-learning systems, and (2) leveraging deep-learning techniques such as large language models to improve software reliability and productivity.

I will use projects and papers to illustrate some of the opportunities that we see and the challenges that we face. For example, how can we address the two key challenges of software testing, i.e., automated test generation and oracle generation, for testing deep-learning software? How can we leverage deep-learning techniques to automate and improve challenging software engineering tasks? How can we teach generative-AI models software domain knowledge? Are customized deep-learning models or generic deep-learning models more effective for software testing tasks? How would data leakage and proprietary large language models affect the validity of software engineering research?

Biography:

Lin Tan is a Mary J. Elmore New Frontiers Professor in the Department of Computer Science at Purdue University. She is an ACM Distinguished Member and an IEEE senior member. She received her PhD from the University of Illinois, Urbana-Champaign. Prior to joining Purdue, she was a Canada Research Chair and an associate professor at the University of Waterloo. Her research interests include software dependability, software-AI synergy, and software text analytics. Some of her research focuses are leveraging machine learning and natural language processing techniques to improve software dependability, and using software approaches to improve the dependability of machine learning systems.

Dr. Tan was a recipient of an Early Career Academic Achievement Alumni Award by the University of Illinois, Urbana-Champaign, Canada Research Chair, an NSERC Discovery Accelerator Supplements Award, an Ontario Early Researcher Award, an Ontario Professional Engineers Award–Engineering Medal for Young Engineer, and multiple industry awards including J.P.Morgan AI Faculty Research Awards, Meta/Facebook Research Awards, Google Faculty Research Awards, and an IBM CAS Research Project of the Year Award. Dr. Tan’s co-authored papers have received ACM SIGSOFT Distinguished Paper Awards at ASE 2020, MSR 2018, and FSE 2016; and IEEE Micro’s Top Picks in 2006.

She serves or has served as program (co-)chair of FSE 2024, FSE 2020 Visions & Reflections, ICSE 2019 SMeW, SOSP 2019 Scholarship, MSR 2017, ICSE 2017 NIER, and ICSME 2015 ERA. She was an associate editor of IEEE Transactions on Software Engineering (2017-2022) and Springer Empirical Software Engineering Journal (2015-2021). She is the ACM SIGSOFT Treasurer and an elected Member-at-Large.