While Cave Automatic Virtual Environment (CAVE) systems have long enabled room-scale virtual reality and various kinds of interactivity, their content has largely remained predetermined. We present Storycaster, a generative AI CAVE system that transforms physical rooms into responsive storytelling environments. Unlike headset-based VR, Storycaster preserves spatial awareness, using live camera feeds to augment the walls with cylindrical projections, allowing users to create worlds that blend with their physical surroundings. Additionally, our system enables object-level editing, where physical items in the room can be transformed to their virtual counterparts in a story. A narrator agent guides participants, enabling them to co-create stories that evolve in response to voice commands, with each scene enhanced by generated ambient audio, dialogue, and imagery. Participants in our study (n = 13) found the system highly immersive and engaging, identifying the narrator and audio as the most impactful elements, while also highlighting areas of improvement in latency and image resolution.

Large Language Models (LLMs) are becoming increasingly ubiquitous in daily life, impacting decision-making across various domains. A substantial body of prior work has shown that individuals tend to evaluate positive predictions more favorably than negative ones—a phenomenon often referred to as the personal validation effect—across various non-AI prediction sources. Building on this foundation, we extend this well-established psychological effect to the context of LLM-based predictions, examining how prediction valence influences users’ perceptions when the source is an AI system. We investigate how positive AI-generated responses affect perceived validity, personalization, reliability, and usefulness of chatbot predictions, even when those predictions are fictitious and pre-scripted. In a study of 238 participants, positive predictions were perceived as significantly more valid (36% increase), personalized (42% increase), reliable (27% increase), and useful (22% increase) than negative predictions. These findings demonstrate that the personal validation effect persists in interactions with LLMs and underscore the substantial role of prediction valence in shaping user perceptions, with important implications for the design and deployment of AI systems across diverse applications.

Empathy is increasingly recognized as a key factor in human–AI communication, yet conventional approaches to “digital empathy” often focus on simulating internal, human like emotional states while overlooking the inherently subjective, contextual, and relational facets of empathy as perceived by users. In this work, we propose a human-centered taxonomy that emphasizes observable empathic behaviors and introduce a new dataset, SENSE-7, of real-world conversations between information workers and Large Language Models (LLMs), which includes per-turn empathy annotations directly from the users, along with user characteristics, and contextual details, offering a more user-grounded representation of empathy. Analysis of 695 conversations from 109 participants reveals that empathy judgments are highly individualized, context-sensitive, and vulnerable to disruption when conversational continuity fails or user expectations go unmet. To promote further research, we provide a subset of 672 anonymized conversation and provide exploratory classification analysis, showing that an LLM-based classifier can recognize 5 levels of empathy with an encouraging average Spearman ρ = 0.369 and Accuracy = 0.487 over this set. Overall, our findings underscore the need for AI designs that dynamically tailor empathic behaviors to user contexts and goals, offering a roadmap for future research and practical development of socially attuned, human-centered artificial agents.

CHI ’25, Yokohama, Japan

We present Social Conjurer, a system and framework that enables real-time, AI-augmented creation of virtual 3D environments for multiple users. Unlike prior GenAI systems that focus on single-user workflows or static scenes, Social Conjurer allows co-located or remote users to collaboratively build worlds using natural language, sketches, and tool-based interactions. We integrate LLMs, VLMs, and a custom networked Unity architecture to support spatial reasoning, dynamic asset placement, and shared editing. A study with 12 participants suggests the system enables co-creative worldbuilding.

Information workers increasingly struggle with productivity challenges in modern workplaces, facing difficulties in managing time and effectively utilizing workplace analytics data for behavioral improvement. Despite the availability of productivity metrics through enterprise tools, workers often fail to translate this data into actionable insights. We present a comprehensive, user-centric approach to address these challenges through AI-based productivity agents tailored to users' needs. Utilizing a two-phase method, we first conducted a survey with 363 participants, exploring various aspects of productivity, communication style, agent approach, personality traits, personalization, and privacy. Drawing on the survey insights, we developed a GPT-4 powered personalized productivity agent that utilizes telemetry data gathered via Viva Insights from information workers to provide tailored assistance. We compared its performance with alternative productivity-assistive tools, such as dashboard and narrative, in a study involving 40 participants. Our findings highlight the importance of user-centric design, adaptability, and the balance between personalization and privacy in AI-assisted productivity tools. By building on these insights, our work provides important guidance for developing more effective productivity solutions, ultimately leading to optimized efficiency and user experiences for information workers.

Behind the scenes of maintaining the safety of technology products from harmful and illegal digital content lies unrecognized human labor. The recent rise in the use of generative AI technologies and the accelerating demands to meet responsible AI (RAI) aims necessitates an increased focus on the labor behind such efforts in the age of AI. This study investigates the nature and challenges of content work that supports RAI efforts, or "RAI content work," that spans content moderation, data labeling, and red teaming -- through the lived experiences of content workers. We conduct a formative survey and semi-structured interview studies to develop a conceptualization of RAI content work and a subsequent framework of recommendations for providing holistic support for content workers. We validate our recommendations through a series of workshops with content workers and derive considerations for and examples of implementing such recommendations. We discuss how our framework may guide future innovation to support the well-being and professional development of the RAI content workforce.

The future of work is rapidly changing, with remote and hybrid settings blurring the boundaries between professional and personal life. To understand how work rhythms vary across different work settings, we conducted a month-long study of 65 software developers, collecting anonymized computer activity data as well as daily ratings for perceived stress, productivity, and work setting. In addition to confirming the double-peak pattern of activity at 10:00 am and 2:00 pm observed in prior research, we observed a significant third peak around 9:00 pm. This third peak was associated with higher perceived productivity during remote days but increased stress during onsite and hybrid days, highlighting a nuanced interplay between work demands and work settings. Additionally, we found strong correlations between computer activity, productivity, and stress, including an inverted U-shaped relationship where productivity peaked at around six hours of computer activity before declining on more active days. These findings provide new insights into evolving work rhythms and highlight the impact of different work settings on productivity and stress.

We present AImagery, an AI-powered immersive relaxation experience tailored to user preferences and physiological feedback. In a study with 32 participants, half of them experienced a multisensory experience with scent, biofeedback, and a personalized AI audio story based on their heart rate, self-reported mood and custom scenery. The experimental group showed a significant anxiety reduction for those with moderate to high anxiety, as opposed to the control group (non-guided meditation/baseline resting control condition). User feedback was positive and received high ratings for enjoyment, immersion and, to a lesser extend, sleepiness. Our results highlight the potential of multisensory AI-driven relaxation tools for those with elevated anxiety.

We present Large Language Model for Mixed Reality (LLMR), a framework for the real-time creation and modification of interactive Mixed Reality experiences using LLMs. LLMR leverages novel strategies to tackle difficult cases where ideal training data is scarce, or where the design goal requires the synthesis of internal dynamics, intuitive analysis, or advanced interactivity. Our framework relies on text interaction and the Unity game engine. By incorporating techniques for scene understanding, task planning, self-debugging, and memory management, LLMR outperforms the standard GPT-4 by 4x in average error rate. We demonstrate LLMR’s cross-platform interoperability with several example worlds, and evaluate it on a variety of creation and modification tasks to show that it can produce and edit diverse objects, tools, and scenes. Finally, we conducted a usability study (N=11) with a diverse set that revealed participants had positive experiences with the system and would use it again.

This paper investigates how a smartphone-controlled olfactory wearable might improve memory recall. We conducted a within-subjects experiment with 32 participants using the device and without (control). In the experimental condition, bursts of odor were released during visuo-spatial memory navigation tasks, and replayed during sleep the following night in the subjects’ home. We found that compared to control, there was an improvement in memory performance when using the scent wearable in memory tasks that involved walking in a physical space. Furthermore, participants recalled more objects and translations when re-exposed to the same scent during the recall test, in addition to during sleep. These effects were statistically significant, and, in the object recall task, they also persisted for more than one week. This experiment demonstrates a potential practical application of olfactory interfaces that can interact with a user during wake as well as sleep to support memory.

On-face wearables are currently limited to piercings, tattoos, or interactive makeup that aesthetically enhances the user, and have been minimally used for scent-delivery methods. However, on-face scent interfaces could provide an advantage for personal scent delivery in comparison with other modalities or body locations since they are closer to the nose. In this paper, we present the mechanical and industrial design details of a series of form factors for on-face olfactory wearables that are lightweight and can be adhered to the skin or attached to glasses or piercings. We assessed the usability of three prototypes by testing with 12 participants in a within-subject study design while they were interacting in pairs at a close personal distance. We compare two of these designs with an "off-face" olfactory necklace and evaluate their social acceptance, comfort as well as perceived odor intensity for both the wearer and observer.

Automatic and real-time sleep scoring is necessary to develop user interfaces that trigger stimuli in specific sleep stages. However, most automatic sleep scoring systems have been focused on offline data analysis. We present the first, real-time sleep staging system that uses deep learning without the need for servers in a smartphone application for a wearable EEG. We employ real-time adaptation of a single channel Electroencephalography (EEG) to infer from a Time-Distributed Convolutional Neural Network (CNN). Polysomnography (PSG) -the gold standard for sleep staging-requires a human scorer and is both complex and resource-intensive. Our work demonstrates an end-to-end, smartphone-based pipeline that can infer sleep stages in just single 30-second epochs, with an overall accuracy of 83.5% on 20-fold cross validation for 5-stage classification of sleep stages using the open Sleep-EDF dataset. For comparison, inter-rater reliability among sleep-scoring experts is about 80% (Cohen's k=0\pmb.68 to \pmb0.76). We further propose an on-device metric independent of the deep learning model which increases the average accuracy of classifying deep-sleep (N3) to more than 97.2% on 4 test nights using power spectral analysis.

The ability to relax is sometimes challenging to achieve, nevertheless it is extremely important for mental and physical health, particularly to effectively manage stress and anxiety. We propose a virtual reality experience that integrates a wearable, low-cost EEG headband and an olfactory necklace that passively promotes relaxation. The physiological response was measured from the EEG signal. Relaxation scores were computed from EEG frequency bands associated with a relaxed mental state using an entropy-based signal processing approach. The subjective perception of relaxation was determined using a questionnaire. A user study involving 12 subjects showed that the subjective perception of relaxation increased by 26.1 % when using a VR headset with the olfactory necklace, compared to not being exposed to any stimulus. Similarly, the physiological response also increased by 25.0 %. The presented work is the first Virtual Reality Therapy system that uses scent in a wearable manner and proves its effectiveness to increase relaxation in everyday life situations.

The sense of smell is perhaps the most pervasive of all senses, but it is also one of the least understood and least exploited in HCI. We present Essence, the first olfactory computational necklace that can be remotely controlled through a smartphone and can vary the intensity and frequency of the released scent based on biometric or contextual data. This paper discusses the role of smell in designing pervasive systems that affect one's mood and cognitive performance while being asleep or awake. We present a set of applications for this type of technology as well as the implementation of the olfactory display and the supporting software. We also discuss the results of an initial test of the prototype that show the robustness and usability of Essence while wearing it for long periods of time in multiple environments.

We present TactileVR, a proof-of-concept virtual reality system in which a user is free to move around and interact with physical objects and toys, which are represented in the virtual world. By integrating tracking information from the head, hands and feet of the user, as well as the objects, we infer complex gestures and interactions such as shaking a toy, rotating a steering wheel, or clapping your hands. We create educational and recreational experiences for kids, which promote exploration and discovery, while feeling intuitive and safe. In each experience objects have a unique appearance and behavior e.g. in an electric circuits lab toy blocks serve as switches, batteries and light bulbs.We conducted a user study with children ages 5–11, who experienced TactileVR and interacted with virtual proxies of physical objects. Children took instantly to the TactileVR environment, intuitively discovered a variety of interactions, and completed tasks faster than with non-tactile virtual objects. Moreover, the presence of physical toys created the opportunity for collaborative play, even when only some of the kids were using a VR headset.

Wearable commodities are able to extend beyond the temporal span of a particular community event, offering omnipresent vehicles for producing icebreaking interaction opportunities. We introduce a novel platform, which generates social affordances to facilitate community organizers in aggregating social interaction among unacquainted, collocated members beyond initial hosted gatherings. To support these efforts, we present functional work-in-progress prototypes for Social Textiles, wearable computing textiles which enable social messaging and peripheral social awareness on non-emissive digitally linked shirts. The shirts serve as catalysts for different social depths as they reveal common interests (mediated by community organizers), based on the physical proximity of users. We provide 3 key scenarios, which demonstrate the user experience envisioned with our system. We present a conceptual framework, which shows how different community organizers across domains such as universities, brand communities and digital self-organized communities can benefit from our technology.

clayodor (\klei-o-dor\) is a clay-like malleable material that changes smell based on user manipulation of its shape. This work explores the tangibility of shape changing materials to capture smell, an ephemeral and intangible sensory input. We present the design of a proof-of-concept prototype, and discussions on the challenges of navigating smell though form.