Aligning text-to-image generation with user intent remains challenging, as users frequently provide ambiguous inputs and struggle with model idiosyncrasies. We propose Adaptive Prompt Elicitation (APE), a technique that adaptively poses visual queries to help users refine prompts without extensive writing. Our technical contribution is a formulation of interactive intent inference under an information-theoretic framework. APE represents latent user intent as interpretable feature requirements using language model priors, adaptively generates visual queries, and compiles elicited requirements into effective prompts. Evaluation on IDEA-Bench and DesignBench shows that APE achieves stronger alignment with improved efficiency. A user study with 128 participants on user-defined tasks demonstrates 19.8% higher perceived alignment without increased workload. Our work contributes a principled approach to prompting that offers an effective and efficient complement to the prevailing prompt-based interaction paradigm with text-to-image models.

Eligibility criteria play a critical role in clinical trials by determining the target patient population, which significantly influences the outcomes of medical interventions. However, current approaches for designing eligibility criteria have limitations to support interactive exploration of the large space of eligibility criteria. They also ignore incorporating detailed characteristics from the original electronic health record (EHR) data for criteria refinement. To address these limitations, we proposed TrialCompass, a visual analytics system integrating a novel workflow, which can empower clinicians to iteratively explore the vast space of eligibility criteria through knowledge-driven and outcome-driven approaches. TrialCompass supports history-tracking to help clinicians trace the evolution of their adjustments and decisions when exploring various forms of data (i.e., eligibility criteria, outcome metrics, and detailed characteristics of original EHR data) through these two approaches. This feature can help clinicians comprehend the impact of eligibility criteria on outcome metrics and patient characteristics, which facilitates systematic refinement of eligibility criteria. Using a real-world dataset, we demonstrated the effectiveness of TrialCompass in providing insights into designing eligibility criteria for septic shock and sepsis-associated acute kidney injury. We also discussed the research prospects of applying visual analytics to clinical trials.

By overlaying time-synced user comments on videos, Danmu creates a co-watching experience for online viewers. However, its visual-centric design poses significant challenges for blind and low vision (BLV) viewers. Our formative study identified three primary challenges that hinder BLV viewers' engagement with Danmu: the lack of visual context, the speech interference between comments and videos, and the disorganization of comments. To address these challenges, we present DanmuA11y, a system that makes Danmu accessible by transforming it into multi-viewer audio discussions. DanmuA11y incorporates three core features: (1) Augmenting Danmu with visual context, (2) Seamlessly integrating Danmu into videos, and (3) Presenting Danmu via multi-viewer discussions. Evaluation with twelve BLV viewers demonstrated that DanmuA11y significantly improved Danmu comprehension, provided smooth viewing experiences, and fostered social connections among viewers. We further highlight implications for enhancing commentary accessibility in video-based social media and live-streaming platforms.

Publisher Copyright: © 2025 Copyright held by the owner/author(s).

Figure 1: Branch Explorer transforms 360° videos into branching narratives-stories that dynamically unfold based on viewer choices-to create an engaging experience for blind and low vision (BLV) users.It employs a multi-modal machine learning pipeline to generate diverse narrative paths, enabling BLV users to make choices at key branching points and explore each storyline through immersive audio guidance.The figure shows the 360° video HELP (available at: https://youtu.be/G-XZhKqQAHU).

Curators face challenges in selecting, ideating, coordinating, and publicizing exhibited works. Recent advances in GenAI has shaped the role of curators in the exhibition design and production process, leading to new adaptations in the exploration, design, planning, and dissemination phases. To explore the impact of GenAI on curatorial practice, we interviewed 13 curators and followed an additional 3 curators in real-world online exhibition production process. We found that GenAI can support theme selection, space design, topic research, artwork selection, and element production. However, GenAI may also stifling critical thinking, perpetuate inaccuracies, leading to fragmented workflows, misperceptions of feasbility, and concerns about copyright. The effectiveness of GenAI tools often depends on the curator’s understanding of their roles and limitations. This work offer practical design recommendations for curators and suggest future research to design for adopting the use of GenAI in technology-mediated curatorial workflows.

Traditional Medicine (TM) is the oldest healthcare form and has been increasingly adopted as the primary or complementary medical therapy in the world. However, TM's practical development remains highly challenging. While artificial intelligence (AI) has become powerful in advancing modern medicine, limited attention has been paid to its potential and usage in TM. This study addresses this gap through a probe-based interview study with 16 TM clinicians, examining their experiences, perceptions, and expectations of AI-empowered clinical support systems. Our findings reveal that despite numerous AI-CDS systems, their practical usage in TM settings was still limited. We identify a series of practical challenges when integrating AI-CDS into TM clinical scenarios, largely due to TM's unique features and the significant data work challenges these features present. We end by critically discussing the potential issues that may arise when integrating AI into practical TM scenarios, and proposing a series of practical recommendations for future studies.

Virtual reality (VR) is increasingly used as a social platform for users to interact and build connections with one another in an immersive virtual environment. Reflecting on the empirical progress in this area of study, a comprehensive review of how VR could be used to support social interaction is required to consolidate existing practices and identify research gaps to inspire future studies. In this work, we conducted a systematic review of 94 publications in the HCI field to examine how VR is designed and evaluated for social purposes. We found that VR influences social interaction through self-representation, interpersonal interactions, and interaction environments. We summarized four positive effects of using VR for socializing, which are relaxation, engagement, intimacy, and accessibility, and showed that it could also negatively affect user social experiences by intensifying harassment experiences and amplifying privacy concerns. We introduce an evaluation framework that outlines the key aspects of social experience: intrapersonal, interpersonal, and interaction experiences. According to the results, we uncover several research gaps and propose future directions for designing and developing VR to enhance social experience.

Designing synthetic routes for novel molecules is pivotal in various fields like medicine and chemistry. In this process, researchers need to explore a set of synthetic reactions to transform starting molecules into intermediates step by step until the target novel molecule is obtained. However, designing synthetic routes presents challenges for researchers. First, researchers need to make decisions among numerous possible synthetic reactions at each step, considering various criteria (e.g., yield, experimental duration, and the count of experimental steps) to construct the synthetic route. Second, they must consider the potential impact of one choice at each step on the overall synthetic route. To address these challenges, we proposed SynthLens, a visual analytics system to facilitate the iterative construction of synthetic routes by exploring multiple possibilities for synthetic reactions at each step of construction. Specifically, we have introduced a tree-form visualization in SynthLensto compare and evaluate all the explored routes at various exploration steps, considering both the exploration step and multiple criteria. Our system empowers researchers to consider their construction process comprehensively, guiding them toward promising exploration directions to complete the synthetic route. We validated the usability and effectiveness of SynthLensthrough a quantitative evaluation and expert interviews, highlighting its role in facilitating the design process of synthetic routes. Finally, we discussed the insights of SynthLensto inspire other multi-criteria decision-making scenarios with visual analytics.

The global aging trend compels older adults to navigate the evolving digital landscape, presenting a substantial challenge in mastering smartphone applications. While Augmented Reality (AR) holds promise for enhancing learning and user experience, its role in aiding older adults’ smartphone app exploration remains insufficiently explored. Therefore, we conducted a two-phase study: (1) a workshop with 18 older adults to identify app exploration challenges and potential AR interventions, and (2) tech-probe participatory design sessions with 15 participants to co-create AR support tools. Our research highlights AR’s effectiveness in reducing physical and cognitive strain among older adults during app exploration, especially during multi-app usage and the trial-and-error learning process. We also examined their interactional experiences with AR, yielding design considerations on tailoring AR tools for smartphone app exploration. Ultimately, our study unveils the prospective landscape of AR in supporting the older demographic, both presently and in future scenarios.

Reminiscing with photo collections offers significant psychological benefits but poses challenges for people with visual impairment (PVI). Their current reliance on sighted help restricts the flexibility of this activity. In response, we explored using a chatbot in a preliminary study. We identified two primary challenges that hinder effective reminiscence with a chatbot: the scattering of information and a lack of proactive guidance. To address these limitations, we present Memory Reviver, a proactive chatbot that helps PVI reminisce with a photo collection through natural language communication. Memory Reviver incorporates two novel features: (1) a Memory Tree, which uses a hierarchical structure to organize the information in a photo collection; and (2) a Proactive Strategy, which actively delivers information to users at proper conversation rounds. Evaluation with twelve PVI demonstrated that Memory Reviver effectively facilitated engaging reminiscence, enhanced understanding of photo collections, and delivered natural conversational experiences. Based on our findings, we distill implications for supporting photo reminiscence and designing chatbots for PVI.

Despite the rise of digital libraries and online reading platforms, physical libraries still offer unique benefits for education and community engagement. However, due to the convenience of digital resources, physical library visits, especially by college students, have declined. This underscores the need to better engage these users. Augmented Reality (AR) could potentially bridge the gap between the physical and digital worlds. In this paper, we present Augmented Library, an HMD-based AR system designed to revitalize the physical library experience. By creating interactive features that enhance book discovery, encourage community engagement, and cater to diverse user needs, Augmented Library combines digital convenience with physical libraries’ rich experiences. This paper discusses the development of the system and preliminary user feedback on its impact on student engagement in physical libraries. © 2024 Copyright held by the owner/author(s).

Hearing loss affects 20% of the global population, a rate that is increasing dramatically as the world's population ages. Early prevention and identification of ear diseases can significantly reduce the risk of becoming disabled with hearing impairment. We propose EarMonitor, an interactive, vision-based ear health monitoring system that enables users to examine their ear conditions with a low-cost hand-held endoscope. EarMonitor can detect six ear health conditions suitable for self-assessment. It can particularly recognize complications from ear diseases, helping users better understand the results. In the wild, our computer vision algorithm achieves a detection sensitivity of 0.949 for earwax buildup and blockage in 100 external auditory canal photos; our deep learning model achieves an average detection sensitivity of 0.861 for the other five conditions considering complications in 350 tympanic membrane photos. We validated EarMonitor 's effectiveness through a user study involving 17 participants and two experts, leading to valuable insights regarding the design and interpretation of non-clinical assessment devices.

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.

When living apart, grandparents and grandchildren often use audio-visual communication approaches to stay connected. However, these approaches seldom provide sufficient companionship and intimacy due to a lack of co-presence and spatial interaction, which can be fulfilled by immersive virtual reality (VR). To understand how grandparents and grandchildren might leverage VR to facilitate their remote communication and better inform future design, we conducted a user-centered participatory design study with twelve pairs of grandparents and grandchildren. Results show that VR affords casual and equal communication by reducing the generational gap, and promotes conversation by offering shared activities as bridges for connection. Participants preferred resemblant appearances on avatars for conveying well-being but created ideal selves for gaining playfulness. Based on the results, we contribute eight design implications that inform future VR-based grandparent-grandchild communications.

Loving-kindness meditation (LKM) is used in clinical psychology for couples' relationship therapy, but physical isolation can make the relationship more strained and inaccessible to LKM. Virtual reality (VR) can provide immersive LKM activities for long-distance couples. However, no suitable commercial VR applications for couples exist to engage in LKM activities of long-distance. This paper organized a series of workshops with couples to build a prototype of a couple-preferred LKM app. Through analysis of participants' design works and semi-structured interviews, we derived design considerations for such VR apps and created a prototype for couples to experience. We conducted a study with couples to understand their experiences of performing LKM using the VR prototype and a traditional video conferencing tool. Results show that LKM session utilizing both tools has a positive effect on the intimate relationship and the VR prototype is a more preferable tool for long-term use. We believe our experience can inform future researchers.

Managing finances is crucial for older adults who are retired and may rely on savings to ensure their lives’ quality. As digital banking platforms (e.g., mobile apps, electronic payment) gradually replace physical ones, it is critical to understand how they adapt to digital banking and the potential frictions they experience. We conducted semi-structured interviews with 16 older adults in China, where the aging population is the largest and digital banking grows fast. We also interviewed bank employees to gain complementary perspectives of these help givers. Our findings show that older adults used both physical and digital platforms as an ecosystem based on perceived pros and cons. Perceived usefulness, self-confidence, and social influence were key motivators for learning digital banking. They experienced app-related (e.g., insufficient error-recovery support) and user-related challenges (e.g., trust, security and privacy concerns, low perceived self-efficacy) and developed coping strategies. We discuss design considerations to improve their banking experiences.

Analysis is a key part of usability testing where UX practitioners seek to identify usability problems and generate redesign suggestions. Although previous research reported how analysis was conducted, the findings were typically focused on individual analysis or based on a small number of professionals in specific geographic regions. We conducted an online international survey of 279 UX practitioners on their practices and challenges while collaborating during data analysis. We found that UX practitioners were often under time pressure to conduct analysis and adopted three modes of collaboration: independently analyze different portions of the data and then collaborate, collaboratively analyze the session with little or no independent analysis, and independently analyze the same set of data and then collaborate. Moreover, most encountered challenges related to lack of resources, disagreements with colleagues regarding usability problems, and difficulty merging analysis from multiple practitioners. We discuss design implications to better support collaborative data analysis.

The banking industry has been integrating digital technologies globally. However, accepting new technologies is challenging in particular for older adults. We focus on older adults’ banking experiences in China, where digital transactions have been growing rapidly, to provide a perspective on how they adapt to this trend. We conducted an online survey with 155 older adults who are 60 or above (M = 70, SD = 9) from 18 provinces to explore their banking practices and challenges. Our results show that older adults conduct banking transactions frequently. However, few do so using digital platforms despite long wait times in physical banks. The main concerns reported by them are about security and usability. Nonetheless, they hold a positive attitude towards digital platforms (e.g., apps, virtual banks). Interestingly, age and gender have significant effects on particular banking behaviors. We discuss our findings in the context of prior studies and highlight design opportunities for improving banking accessibility for older adults.

As one of the fundamental techniques for image editing, image cropping discards irrelevant contents and remains the pleasing portions of the image to enhance the overall composition and achieve better visual/aesthetic perception. In this paper, we primarily focus on improving the efficiency of automatic image cropping, and on further exploring its potential in public datasets with high accuracy. From this perspective, we propose a deep learning based framework to learn the objects composition from photos with high aesthetic qualities, where an interested object region is detected through a convolutional neural network (CNN) based on the saliency map. The features of the detected interested objects are then fed into a regression network to obtain the final cropping result. Unlike the conventional methods that multiple candidates are proposed and evaluated iteratively, only a single interested object region is produced in our model, which is mapped to the final output directly. Thus, low computational resources are required for the proposed approach. The experimental results on the public datasets show that as a weakly supervised method, the proposed network outperforms the other weakly supervised methods on FLMS and FCD datasets and achieves comparable results to the existing methods on CUHK dataset. Furthermore, the proposed method is more efficient than these methods, where the processing speed is as fast as 20 ms per image.