Talk Title: Intent-AI Interaction: Elevating Human-Computer Interaction to the Intent and Conceptual Level

Speaker:  Jason Ding

Location: HBK 2105 and Zoom

Abstract:  Technological advancements are continually reshaping human-computer interaction (HCI). Although direct manipulation methods, such as clicking and dragging icons in graphical user interfaces (GUIs), remain widespread, generative AI now has the ability to understand user interfaces and autonomously perform tasks. This reduces the reliance on direct user manipulation and prompts a reimagining of HCI paradigm. In this talk, we introduce “intent-AI interaction” as a forward-looking paradigm where interactions are driven by the user’s intent and conceptual reasoning rather than command-level actions. We will demonstrate this paradigm shift through three studies: human-AI co-creation of news headlines, ideation enabled by cross-domain analogies, and data exploration.

Bio:  Zijian “Jason” Ding is a 4th-year PhD candidate at the University of Maryland’s Human-Computer Interaction Lab. His research focuses on intent-AI interaction as a new paradigm in human-computer interaction. His work has been published in top-tier AI and HCI conferences, including EMNLP, CHI, CSCW, and UIST, with recognition such as a best paper honorable mention from ACM Creativity & Cognition. Ding’s industry experience includes internships at Microsoft Research, the MIT-IBM Watson AI Lab (IBM Research), and Dataminr, where his work led to publications, first-authored patents, and real-world products.