241 papers
This paper presents a privacy-preserving vision-language framework for medical interpreter robots that leverages locally deployed open-source LLMs and a novel annotated dataset to accurately detect clinical speech acts and generate human-like, appropriate robotic gestures.
This study evaluates a dual-calibration algorithmic nudge and an LLM-based presentation nudge within a personalized diversity framework, finding that while algorithmic nudges effectively increase news consumption diversity and shift long-term reading habits toward balanced domestic and global coverage, LLM-based presentation nudges yield variable results and user-specific topic interest remains the strongest predictor of engagement.
This paper presents a closed-loop CPR training glove that integrates high-resolution tactile sensing and vibrotactile feedback to enable self-directed practice by accurately estimating compression metrics and providing immediate haptic guidance, thereby reducing reliance on external visual displays.
This paper presents Lexara, a user-centered toolkit designed to address the challenges of evaluating Large Language Models for Conversational Visual Analytics by providing real-world test cases, interpretable multi-format metrics, and an interactive interface that enables developers and end-users to assess model performance without programming expertise.
Through design workshops with 15 UX designers, this paper argues that AI adoption is not merely an efficiency-driven process but a complex negotiation of values across individual, team, and organizational scales that reconfigures roles, power dynamics, and worker agency.
This paper introduces "Glass Chirolytics," a system that overlays visualization and interface widgets onto mirrored video feeds to enable face-to-face remote collaborators to simultaneously manipulate data using bimanual gestures, thereby enhancing feelings of presence and mutual awareness of analytical intent compared to traditional screen-sharing methods.
This paper presents a framework of 16 challenges faced in synchronous and remote collaborative visualization, derived from the insights of 29 international experts across five key collaborative activities and organized to guide future research in technological choices, social factors, AI assistance, and evaluation.
This paper presents a user study demonstrating that human perceptions of fairness in AI systems are shaped not just by statistical parity or outcomes, but significantly by beliefs about the underlying causes of disparities, specifically how infra-marginality and data distribution differences influence judgments in medical decision-making scenarios.
This paper presents and validates an adaptive mixed reality notification system that dynamically adjusts message placement based on urgency levels, demonstrating through user studies that this approach significantly reduces mental workload and frustration while maintaining effective awareness compared to traditional centralized displays.
This paper introduces LongNAP, a user model that leverages a large-scale dataset of 360K annotated multimodal interactions and a hybrid parametric-in-context learning approach to significantly outperform existing baselines in predicting a user's next action by reasoning over their full interaction history.
This paper demonstrates that addressing the ecological fallacy by modeling an author's language context through a specific task called HuLM, particularly during fine-tuning (HuFT) or continued pre-training, significantly improves the performance of an 8B Llama model across multiple downstream tasks compared to standard training methods.
This paper proposes an interpretable modeling approach that integrates person-level psychological traits with situational context features derived from social media data to predict dynamic mental well-being, demonstrating that theory-driven methods offer competitive performance and greater human-understandable insights compared to standard language model embeddings.
This paper proposes a hierarchical resource-rational framework that unifies eye movement control and comprehension during reading by positing that the brain optimizes these processes across nested time scales to maximize understanding while minimizing cognitive and temporal costs, a model that successfully replicates a wide range of human reading behaviors.
This paper introduces ProxyMe, a VR prototype that explores the concept of "avatar self-extension" by allowing users to embody AI-modified avatars, thereby investigating how AI-mediated speech augmentation influences perceptions of agency, authorship, and self-identification.
This paper introduces XIA, an explainable intelligent assessment platform that uses visualized cognitive diagnostic reasoning to help pre-service teachers shift from opaque score-based judgments to evidence-based reasoning, thereby enhancing their assessment literacy through improved reflection and self-regulation.
This paper introduces a skill-adaptive ghost instructor in VR piano training that dynamically adjusts its opacity based on learner performance, demonstrating through a user study that this approach improves pitch and fingering accuracy while reducing over-reliance on cues compared to static guidance.
This exploratory study with 12 elementary students demonstrates that socially assistive robots can effectively facilitate peer mediation role-play for conflict resolution, yielding positive student feedback and revealing significant correlations between trait and learning measures in the robot condition despite the lack of statistical differences compared to a tablet-only control.
A four-week field study comparing contextual bandits and Large Language Models for personalized health interventions reveals that while unconstrained LLMs significantly outperform template-based systems in perceived helpfulness due to their ability to acknowledge user context, they fail to systematically explore diverse behavior change techniques, highlighting a critical design trade-off between structured exploration and generative autonomy in reflective AI health systems.
This paper proposes and validates a set of 16 design guidelines for creating intuitive VR avatars that effectively communicate augmented capabilities and their activation methods, demonstrating that these guidelines significantly improve the clarity and intuitiveness of user interactions across various applications.
This paper introduces "The Pen," an ear-worn wearable AI device designed for episodic, on-demand cognitive assistance that prioritizes user agency, social comfort, and privacy through intentional activation boundaries and local processing.