Intelligent User Interfaces

The Intelligent User Interface research group aims to improve AI system usability by designing innovative, safe, and reliable interfaces for diverse areas such as mobility, industry, healthcare, sustainable behavior, workplaces, and personal life. With the ubiquitous presence of technology, developing cohesive strategies for interacting with devices, services, and applications is essential. Our research group utilizes reinforcement learning, computational rationality, or generative AI to design, implement, and evaluate next-generation interfaces. We focus on managing user attention, accurately modeling human behavior, and dynamically adapting interfaces to align with users’ unique contexts, goals, and ongoing activities.

:read more

AITentive: AI-supported Attentive User Interfaces (FWF)

Human attention is a valuable resource, yet unlike the increasing power of the tech competing for it, attention is limited. Some view our “always-on” culture as akin to addiction, driven by platforms trying to maximize screen time. Today, many people juggle multiple conversations and media, a behavior intensified by digital notifications that constantly interrupt. This […]

AttDrive: Attention Management Systems for Supervisory Control in Driver-Vehicle Interacion (FFG)

Automated vehicles (AVs) promise safer, more efficient transportation, but current systems still require humans to supervise and take control when needed—particularly in SAE Level 2 and 3 automation. Monitoring these systems, however, is an inherently tedious and error-prone task, especially as drivers become distracted by non-driving related tasks like using smartphones or reading. This “supervisory […]

MemAgent: Cognitive Models for Human-Like Decision-Making (IT:U Seed)

Human decisions are shaped by memory processes – what we know, what we forget, and how we retrieve information in context. Still, most AI systems treat human cognition as static or overly simplified, ignoring the nuanced ways people recall knowledge and apply rules in dynamic environments. While recent advances in generative agents can partly simulate […]