Large Language Models (LLMs) are expected to enhance medical education through personalized clinical skills training. However, their practical application from the student user experience perspective remains underexplored. This gap is critical because without understanding students’ needs, LLM-based tools risk poor adoption and suboptimal learning outcomes. This study explores medical students’ challenges and expectations when using LLM-based clinical skills training through a two-phase investigation involving 14 medical students. We integrated five Type 2 Diabetes cases into a probe platform and conducted probe-based studies followed by co-design workshops. We identified challenges across three categories: dialogue content (lack of realism, insufficient knowledge depth differentiation); dialogue presentation (information overload, single modality limitations); and dialogue interaction (inadequate guidance and feedback). Co-design workshops revealed expectations for enhanced patient modeling, personalized content delivery, structured presentation frameworks, and collaborative features. These findings provide design considerations for developing more effective, user-centered LLM-based medical education systems.

Voice agents can construct meaningful conversations with older adults to offer various benefits, such as providing emotional companionship and assisting with memory recall. However, such conversations often follow the simple turn-taking pattern and lack interruption and backchannel of natural human conversation. Previous research has shown that this rigid turn-taking pattern lacks interactivity and initiative, limiting the flexible communication between older adults and voice agents. To address these issues and create a more natural conversational voice agent, we first conducted a formative study to identify common usage of interruption in the natural conversations of older adults. We then designed an LLM-powered Barge-in agent that supports interruption and backchannel. Our within-subject exploratory study showed that participants felt that conversations with Barge-in agents were more natural, engaging, and fluent than with the No barge-in agent. We further present design implications for creating more natural and human-like voice agents for older adults.

As the global population ages, comprehensively assessing older adults' physical, cognitive, and social capacities is increasingly crucial for guiding care decisions and resource allocation.While technology shows promise in enhancing these assessments, there is limited understanding of how practitioners conduct such assessments and how they perceive and experience assessment technologies in real-world settings.This paper presents an exploratory study of the practices and experiences of practitioners in China's Ability Assessment of Older Adults (AAOA), based on 28 on-site observations and in-depth interviews with eight assessors in a large southeastern city.Our findings reveal the adaptive workflows, strategies, and diverse challenges faced by assessors, highlighting the complexity, context-specificity, and collaborative nature of these processes.While grounded in China's evolving healthcare system, these findings also resonate with broader global challenges in aging care, particularly in resource-constrained settings.Based on these insights, we propose implications for designing practical assessment technologies and considerations for better supporting assessors and older adults across care contexts.

This study investigates the use of generative AI with the Rorschach Inkblot Test to support emotional exploration and self-expression. A controlled experiment compared static images with AI-generated dynamic visuals, and expert interviews provided professional insights. Results indicate that dynamic visuals can deepen emotional exploration, enrich narratives, and expand self-expression, though individual differences and content variability remain challenges. This work offers a novel methodology for integrating generative AI into psychological assessment and creative arts while highlighting its potential and ethical considerations.

People who are deaf or hard of hearing (DHH) in China are increasingly exploring online platforms to connect with potential partners. This research explores the online dating experiences of DHH communities in China, an area that has not been extensively researched. We interviewed sixteen participants who have varying levels of hearing ability and love-seeking statuses to understand how they manage their identities and communicate with potential partners online. We find that DHH individuals made great efforts to navigate the rich modality features to seek love online. Participants used both algorithm-based dating apps and community-based platforms like forums and WeChat to facilitate initial encounters through text-based functions that minimized the need for auditory interaction, thus fostering a more equitable starting point. Community-based platforms were found to facilitate more in-depth communication and excelled in fostering trust and authenticity, providing a more secure environment for genuine relationships. Design recommendations are proposed to enhance the accessibility and inclusiveness of online dating platforms for DHH individuals in China. This research sheds light on the benefits and challenges of online dating for DHH individuals in China and provides guidance for platform developers and researchers to enhance user experience in this area.

Recent studies show the promise of VR in improving physical, cognitive, and emotional health of older adults. However, prior work on optimizing object selection and manipulation performance in VR was mostly conducted among younger adults. It remains unclear how older adults would perform such tasks compared to younger adults and the challenges they might face. To fill in this gap, we conducted two studies with both older and younger adults to understand their performances and user experiences of object selection and manipulation in VR respectively. Based on the results, we delineated interaction difficulties that older adults exhibited in VR and identified multiple factors, such as headset-related neck fatigue, extra head movements from out-of-view interactions, and slow spatial perceptions, that significantly decreased the motor performance of older adults. We further proposed design recommendations for improving the accessibility of direct interaction experiences in VR for older adults.

With the development of digital technology, tourists have higher expectations for their experiences with digital cultural heritage (CH). However, there is limited research and design guidelines on how to effectively convey expert knowledge and transfer the value and connotations of digital CH to users in a virtual environment. Based on existing literature, we proposed a systematic design strategy for immersive virtual reality (IVR) systems, incorporating multimodal interaction, gamification, and storytelling for CH presentation, development, and promotion to the public. Accordingly, taking the virtual restoration of the Dunhuang murals as an example, we developed an IVR system that provided users with learning, interactive, and entertaining experiences, facilitating their transition from mere visitors to active learners while engaging with digital CH. We conducted a between-subjects user study involving 42 participants. The results demonstrated that our IVR system motivated users interests in CH, promoted CH preservation awareness, and could be applied in the domain of digital CH experiences.

Assistive technologies are increasingly developed and applied in exhibition environments to help blind and low vision (BLV) people deal with the challenges they face when visiting exhibitions. While studies have examined the experiences of BLV people using such technologies, little is known about the experiences and challenges of curators incorporating assistive technologies into exhibitions to make them more accessible to BLV people. This research focuses on assistive technologies for BLV people in exhibitions from a curatorial perspective. We conducted semi-structured interviews with twenty-two experienced curators to understand their practices and challenges. We also curated a list of assistive technologies from published papers and used them as probes to seek curators’ attitudes and perceptions of such technologies. We uncovered four critical themes related to curators’ challenges of making exhibitions more accessible to BLV people. We further identified a vicious circle, which prevents curators from making exhibitions more accessible and discussed possible ways to support curators in making exhibitions more accessible to BLV people.