239 papers
This paper introduces XInsight, a multi-agent framework that aligns psychological support with the Exploration-Insight-Action paradigm through a structured Reason-Intervene-Reflect cycle to enhance interpretability and therapeutic effectiveness in digital well-being applications, accompanied by the XInsight-Bench evaluation protocol.
This research demonstrates that the sequence of rating and reviewing significantly polarizes consumer evaluations—amplifying high ratings for good services and low ratings for poor ones—by triggering affective heuristics and varying cognitive effort, a finding validated through experiments and real-world data from platforms like Yelp and Letterboxd.
EyeAgent is a novel agentic AI framework that leverages a large language model to dynamically orchestrate 53 specialized ophthalmic tools across 23 imaging modalities, achieving high diagnostic accuracy and significantly enhancing clinical decision support and report quality for ophthalmologists, particularly juniors, through interpretable and adaptable multimodal analysis.
This study analyzes Italian music listeners' narratives to reveal their routine yet uncritical engagement with recommender systems and limited awareness of gender-related representational harms, arguing for the integration of psychosocial insights into the design of culturally sensitive algorithms.
This study evaluates Shiksha Copilot, an AI-assisted tool deployed in Karnataka, India, which successfully reduced teachers' administrative burdens and stress while fostering activity-based pedagogy through a human-AI collaborative workflow, though its broader pedagogical impact was limited by systemic challenges like staffing shortages.
This paper proposes "Reading Activity Traces" (RATs) to reframe reading as a creative activity by making the interpretive labor of navigating and connecting sources visible, thereby countering the automation of human interpretation through tools like the speculative WikiRAT system.
This paper proposes a task-aware collaboration signaling layer that transforms offline preference evaluations into online, interpretable cues for capability and coordination risk, enabling a closed-loop delegation protocol that enhances human-LLM teamwork through mutual awareness, adaptive routing, and auditable accountability.
The paper introduces "World Mouse," a cross-reality cursor system that bridges the gap between physical and virtual environments by leveraging surface normals and interpolation to enable precise, natural interactions with both real-world and digital objects in Extended Reality.
This study of 25 K-12 teachers reveals that while AI-generated rubrics are valued as time-saving drafts that clarify criteria, educators emphasize the necessity of human oversight to address issues with alignment and customization, ultimately adopting these tools only when workflows preserve teacher control.
This study reveals that while persistent efficacy beliefs drive systematic "AI optimism" and influence delegation decisions, they have a weaker impact on actual human-AI team performance, suggesting that transparency-focused approaches may be insufficient for optimizing collaborative outcomes.
This paper presents the proceedings of the inaugural CHI 2026 workshop held in Barcelona, which aims to disentangle the fragmented politics, values, and imaginaries within Human-Computer Interaction by examining them through the lens of ideologies.
This paper argues that the widespread effectiveness of terminal-based AI agent tools stems from their inherent representational compatibility, transparency, and low barriers to entry, proposing these design properties as essential standards that any future human-AI interface modality must deliberately replicate.
This paper presents a corpus study of 909 word-scale graphics from over 126,000 scientific papers to propose a framework characterizing their positioning, communicative functions, and visual representations, while highlighting their current rarity and potential to enhance scholarly communication.
MoXaRt is a real-time Extended Reality system that leverages a cascaded audio-visual architecture to separate up to five concurrent sound sources, significantly improving speech intelligibility and reducing cognitive load in complex acoustic environments.
This paper introduces AnimaStand, a system that animates smartphones to act as active embodied facilitators in four-stranger group discussions, demonstrating through a Wizard-of-Oz study that such expressive movement re-engages inactive members and enhances overall group dynamics, task performance, and relationships.
This paper presents the first systematic evaluation of self-supervised learning for label-efficient sleep staging using wearable EEG, demonstrating that a specialized SSL pipeline significantly outperforms supervised baselines and general-purpose foundation models by achieving clinical-grade accuracy with only 5–10% of labeled data.
This study utilizes Transition Network Analysis on eye-tracking data from 40 clinicians in VR-based cardiac arrest simulations to demonstrate how visual attention dynamically redistributes across roles and scenario phases, offering a novel framework for modeling team situational awareness and enhancing acute care training.
This paper presents an empirical study demonstrating that personalizing AI-driven hint explanations in an Intelligent Tutoring System for students with low Need for Cognition and Conscientiousness significantly increases their engagement, understanding, and learning outcomes.
This paper presents a platform-agnostic Digital Human Modelling framework that integrates OpenBCI Galea biosensing with a reproducible SuperTux game environment to provide structured, temporally aligned multimodal data for future AI-driven, ethics-approved research in accessibility and inclusive interaction design.
This paper introduces AgentA/B, a novel system that leverages autonomous LLM agents with diverse personas to automatically simulate scalable, interactive user behaviors for web A/B testing, effectively addressing the limitations of traditional methods by emulating human-like interactions without relying on large-scale live traffic.