Candidates for the computer science tenure-track faculty position openings in the College of Computing will be visiting campus this semester, including Jie “JW” Wu.
Bio
Jie “JW” Wu is a postdoctoral fellow at the University of British Columbia. His research lies at the intersection of software engineering (SE) and AI, focusing on Trustworthy AIware (i.e., AI-powered Software). He received his Ph.D. from George Washington University, where he studied automated online controlled experiments. He received his M.S. and B.S. at Shanghai Jiao Tong University. Before his postdoctoral fellowship, he worked as a software engineer for a decade in the industry at Snap Inc., Microsoft, and a startup. He was a research intern at Google Research and Microsoft Research. He has published in top venues, including ACM Transactions on Software Engineering and Methodology, Foundations of Software Engineering, AAAI, IJCAI, etc. His single-author paper was recognized as a Best Paper Award candidate at IEEE/ACM 3rd International Conference on AI Engineering (CAIN 2024). He serves as the Program Committee member of different tracks for SE conferences, including RAIE 2025, CAIN 2025, SANER 2025, ASE 2024, and FSE 2024. More information is available on Wu’s website.
Date and time of visit: Wednesday, March 19, 2025, 3 p.m. ET, followed by a social hour in Rekhi 218
Location: Rekhi G005 or via Zoom at https://michigantech.zoom.us/j/86212992127
Abstract
Building Trustworthy and Safe AIware with Systems Thinking
As we transition from software to AIware (i.e., AI-powered software), ensuring the reliability and safety of AIware becomes paramount, especially in the age of Large Language Models (LLMs). In this talk, I will introduce a systems thinking approach to address trustworthiness issues in AIware, emphasizing the importance of connections, feedback loops, layers, and new processes. I will demonstrate this approach through a series of works. First, I focus on the truthfulness of Code LLMs through a newly developed benchmark called HumanEvalComm, which evaluates their ability to ask clarifying questions. Second, I further highlight the development of the LLM-agent framework, Okanagan, and the instruction fine-tuning method, ClarifyCoder, to enhance the communication skills of Code LLMs. Finally, I share how systems thinking can address the collaboration challenges when building products with AI components.
About the College of Computing
The Michigan Tech College of Computing, established in 2019, is the first academic unit in Michigan dedicated solely to computing, and one of only a handful such academic units in the United States. The college is composed of two academic departments. The Computer Science department offers four bachelor of science programs in computer science, cybersecurity, data science, and software engineering; four master of science programs in applied computer science, computer science, cybersecurity, and data science; and a doctoral program in computer science. The Applied Computing department offers four bachelor of science programs in cybersecurity, electrical engineering technology, information technology, and mechatronics; and two master of science programs in health informatics and mechatronics. The college also helps to administer an interdisciplinary doctoral program in computational science and engineering.Questions? Contact us at computing@mtu.edu.
Follow the College of Computing on Facebook, Instagram, LinkedIn and Twitter.