State of the Field
The field of human-computer interaction is currently focused on enhancing the integration of AI into everyday user experiences, particularly through the lens of Theory of Mind, which aims to create AI that understands and responds to users' mental states. Recent work emphasizes the importance of situating AI within social contexts and adapting to the dynamic nature of user interactions, addressing gaps between practitioners' aspirations and current design practices. Additionally, augmented reading systems are evolving through simulation-based optimization, allowing for real-time personalization and improved comprehension without excessive human intervention. Trust dynamics in generative AI are also under scrutiny, as users increasingly seek emotional support from these systems, highlighting the need for designs that foster trust while maintaining awareness of AI's limitations. Collectively, these developments signal a shift toward more responsive, user-centered AI systems that prioritize adaptability, trust, and effective communication in various applications, from reading to emotional support and professional writing.
Papers
1–8 of 8PleaSQLarify: Visual Pragmatic Repair for Natural Language Database Querying
Natural language database interfaces broaden data access, yet they remain brittle under input ambiguity. Standard approaches often collapse uncertainty into a single query, offering little support for...
Knob: A Physics-Inspired Gating Interface for Interpretable and Controllable Neural Dynamics
Existing neural network calibration methods often treat calibration as a static, post-hoc optimization task. However, this neglects the dynamic and temporal nature of real-world inference. Moreover, e...
Simulation-based Optimization for Augmented Reading
Augmented reading systems aim to adapt text presentation to improve comprehension and task performance, yet existing approaches rely heavily on heuristics, opaque data-driven models, or repeated human...
Situated, Dynamic, and Subjective: Envisioning the Design of Theory-of-Mind-Enabled Everyday AI with Industry Practitioners
Theory of Mind (ToM) -- the ability to infer what others are thinking (e.g., intentions) from observable cues -- is traditionally considered fundamental to human social interactions. This has sparked ...
A Resource-Rational Principle for Modeling Visual Attention Control
Understanding how people allocate visual attention is central to Human-Computer Interaction (HCI), yet existing computational models of attention are often either descriptive, task-specific, or diffic...
Generative Confidants: How do People Experience Trust in Emotional Support from Generative AI?
People are increasingly turning to generative AI (e.g., ChatGPT, Gemini, Copilot) for emotional support and companionship. While trust is likely to play a central role in enabling these informal and u...
Simulating Human Audiovisual Search Behavior
Locating a target based on auditory and visual cues$\unicode{x2013}$such as finding a car in a crowded parking lot or identifying a speaker in a virtual meeting$\unicode{x2013}$requires balancing effo...
Investigating Writing Professionals' Relationships with Generative AI: How Combined Perceptions of Rivalry and Collaboration Shape Work Practices and Outcomes
This study investigates how professional writers' complex relationship with GenAI shapes their work practices and outcomes. Through a cross-sectional survey with writing professionals (n=403) in diver...