UIST Adjunct 2026AI-generated personas are being increasingly used for support, training and simulations. While generative AI models possess abilities to generate affect-aware responses, their embodiment into visual personas is an active area of investigation.
ACM IH 2026Community-engaged dissemination and implementation research focuses on the implementation of evidence-based interventions within clinical or community-based settings. It uses community-engaged processes or partnerships.
ACM IH 2026Designing effective interactive health systems requires rich, realistic data to inform user-centered design activities. However, accessing authentic health data introduces major barriers due to privacy rules (HIPAA, IRBs, data use agreements) governing protected health information.
CHIL 2026
Effective patient-provider communication is difficult to assess at scale. This work examines whether large language models can track 20 social behaviors from clinical transcripts without fine-tuning, and introduces an agreement-weighted ensemble to stabilise performance that otherwise varies by patient race and visit segment.
CHI EA 2026The prevailing response to the student mental health crisis has been to expand clinical capacity: hire more therapists, reduce wait times, increase funding. We challenge this assumption.
ACM IH 2026Universities have expanded counseling capacity in response to rising student mental health needs, yet limited access, fragmented discovery, and weak follow-through remain persistent barriers. Institutions offer non-clinical wellness support, but student awareness and use remain low.
UIST Adjunct 2025Using head-mounted Virtual Reality (VR) displays to simulate driving is critical to study driving behavior and design driver assistance systems. But existing VR driving simulators are often limited to tracking only eye movements.
Stroke 2025Augmented reality enables visualization of and interaction with both physical and virtual environments. Holograms can allow 3‐dimensional image transmission to distant sites, allowing patients to interact with providers as if in the same space. Our prior publication resulted in high satisfaction/immersion for patients interacting with Holo‐Stroke providers. Our aim here was to determine if providers assessing computed tomographic angiographies (CTAs) for large vessel occlusion would result in reliability and satisfaction.
CHI 2025
Emergency Remote Teaching (ERT) during COVID-19 offered a unique chance to study online higher education at scale, beyond traditional lab settings. Through a review of 22 empirical studies, we analyzed how online classrooms addressed different types of interaction. Our findings highlight the need for future research that centers Learner-Content interaction as a way to balance flexibility with structure—especially as ERT may continue to shape education going forward.
CHI 2025
Trust in autonomous vehicles varies widely among individuals, and this study uses machine learning to identify the key factors influencing young adults’ trust. Surveying over 1,400 participants, the analysis reveals that perceptions of AV risks and benefits, usability attitudes, institutional trust, prior experience, and mental models are the strongest predictors of trust—while psychosocial traits and driving styles play a lesser role. These findings underscore the need to account for individual differences when designing trustworthy AV systems.