AIware 2025 Keynote Speakers
Lin Tan
Purdue University
TBA
TBA
Bio: Lin Tan is the Mary J. Elmore New Frontiers Professor of Computer Science at Purdue University, previously a Canada Research Chair and associate professor at the University of Waterloo, with a PhD from the University of Illinois Urbana-Champaign. Her research spans software-AI synergy, LLM4Code, software dependability, autoformalization, and software text analytics, with a particular focus on applying machine learning and natural language processing to improve software reliability and using software methods to enhance the dependability of AI systems. She is an IEEE Fellow, ELATES Fellow, and ACM Distinguished Member, and has received numerous honors, including major academic and industry awards from organizations such as NSERC, Ontario Professional Engineers, J.P. Morgan, Meta, Google, and IBM. Her work has also been recognized through multiple distinguished paper awards and highlights at leading venues including CCS, ASE, MSR, FSE, NeurIPS, AAAI, and ICRA. In addition, she has held significant leadership roles in the research community, serving as program chair or co-chair for major conferences and workshops such as FSE and LLM4Code, as well as in editorial and professional service roles with IEEE TSE, EMSE, and ACM SIGSOFT.
Qidi Xu
MiniMax
From Chatbots to Colleagues: Steering Code-Driven Agents for End-to-End Autonomy
The paradigm of Generative AI is rapidly evolving from passive assistants to autonomous entities. Moving beyond the chatbot and simple code-completion copilots, the next generation of AI agents functions as digital colleagues capable of end-to-end task execution. This talk explores how these agents leverage code not merely as an output, but as their fundamental reasoning engine and interface for interacting with the world. We will focus on the shift from manual prompting to high-level Steering, discussing how human intent can guide code-driven agents to autonomously navigate complex workflows, resolve software engineering challenges, and bridge the gap between abstract requirements and finished, functional results.
Bio: TBA