Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional ModelingRecent advances in foundation models have enabled conversational agents that aim for sustained companionship rather than mere task completion. Yet most still remain unable to support natural, long-term companion-like interactions, resulting in experiences that feel episodic and inauthentic. We argue that current agents overlooked cross-temporal modeling of agents’ social behaviors and internal emotions: generated behaviors rarely influence an agent’s emotional state, and emotional states seldom shape subsequent behaviors. We present Cross-Temporal Emotion Modeling (CTEM), a framework that links long-term behavioral history to moment-to-moment emotional expression. CTEM establishes a closed loop where past experiences update an evolving emotional state; this state conditions immediate interactions; and user feedback continually revises both memory and emotional state, enabling reflection and anticipation. We instantiate CTEM as \textit{Auri}, a companion agent on an instant-messaging platform, and report a 21-day in-the-wild study showing that CTEM shows improvements in perceived naturalness, coherence, and emotional harmony.2026YZYi Zheng et al.Communication University of ChinaAgent Personality & AnthropomorphismAffective Human-Computer DialogueHuman-LLM CollaborationCHI
Intrinsic vs. Extrinsic Programming Challenges in Educational Games: How they shape Children’s Computational Thinking, Learning Drive, and Game EngagementEducational programming games (EPGs) build computational thinking (CT), a vital 21st-century skill. A core design challenge is how pedagogical and gameplay challenges are integrated to balance educational objectives with player engagement. This study formalizes two contrasting challenge design patterns that reflect distinct integration strategies: extrinsic programming challenges (C1), a pedagogy-oriented design where programming is the core challenge enforced through external constraints; and intrinsic programming challenges (C2), a gameplay-oriented design where programming serves as a tool for overcoming gameplay challenges raised by in-game puzzles. To examine these challenge design patterns, we developed two isomorphic EPGs WannaBone1 (C1) and WannaBone2 (C2), each featuring 20 levels introducing sequences, loops, conditionals, and global variables. A controlled classroom study with 306 primary school students reveals that both designs improve CT, whereas C2 yields significantly higher intrinsic learning motivation and high-order immersion of flow. These findings indicate that a gameplay-oriented rather than pedagogy-oriented design perspective better unites education and entertainment, guiding future EPGs design.2026BCBaijun Chen et al.Beijing University of Posts and TelecommunicationsProgramming Education & Computational ThinkingSerious & Functional GamesCHI
"I recall the past": Exploring How People Collaborate with Generative AI to Create Cultural Heritage NarrativesVisitors to cultural heritage sites often encounter official information, while local people's unofficial stories remain invisible. To explore generative AI's potential in assisting individuals to access local narratives, we conducted a workshop with 20 participants, asking them to use Stable Diffusion to create images of familiar cultural heritage sites, as well as images of unfamiliar ones for comparison. The results revealed three narrative strategies and highlighted generative AI's strengths in illuminating, amplifying, and reinterpreting personal narratives. However, the AI showed limitations in meeting detailed requirements, portraying cultural features, and avoiding bias, which were particularly pronounced with unfamiliar sites due to participants' lack of local knowledge. To address these challenges, we recommend providing detailed explanations, prompt engineering, and fine-tuning AI models to reduce uncertainties, using objective references to mitigate inaccuracies from participants' inability to recognize errors or misconceptions, and curating datasets to train AI models capable of accurately portraying cultural features.2025ZHZhiting He et al.Games, Entertainment, & CultureCSCW
From Words to Wonder: Designing and Evaluating an AI-Empowered Creative Storytelling System for Elementary ChildrenWhile several digital tools exist for children’s creative storytelling, few have explored how generative AI can enhance storytelling quality. Our formative research identified five design requirements for AI-powered storytelling tools for elementary students. We developed a system named StoryPrompt that enables children to co-create stories and comics with AI, boosting literacy and creativity. Pilot tests with children and HCI experts demonstrated good usability and positive learning experiences. In a mixed-methods evaluation with 40 children from Grades 2-6, we found that StoryPrompt significantly improved storytelling creativity and richness, compared to the storyboard method. Observations indicated more purposeful planning and strategic use of AI-generated words and images, facilitating efficient exploration of storytelling alternatives. While children preferred AI images, they recognized the limitations in representing storytelling details. Teacher interviews highlighted the system’s motivational potential and classroom flexibility. We discuss the benefits and considerations of using generative AI to enhance creative storytelling for children.2025MFMin Fan et al.Communication University of China, School of Animation and Digital ArtsGenerative AI (Text, Image, Music, Video)Gamification DesignSTEM Education & Science CommunicationCHI
How Users Who are Blind or Low Vision Play Mobile Games: Perceptions, Challenges, and StrategiesAs blind and low-vision (BLV) players engage more deeply with games, accessibility features have become essential. While some research has explored tools and strategies to enhance game accessibility, the specific experiences of these players with mobile games remain underexamined. This study addresses this gap by investigating how BLV users experience mobile games with varying accessibility levels. Through interviews with 32 experienced BLV mobile players, we explore their perceptions, challenges, and strategies for engaging with mobile games. Our findings reveal that BLV players turn to mobile games to alleviate boredom, achieve a sense of accomplishment, and build social connections, but face barriers depending on the game's accessibility level. We also compare mobile games to other forms of gaming, highlighting the relative advantages of mobile games, such as the inherent accessibility of smartphones. This study contributes to understanding BLV mobile gaming experiences and provides insights for enhancing accessible mobile game design.2025ZRZihe Ran et al.Communication university of ChinaAccessible GamingGame AccessibilityCHI
RemapVR: An Immersive Authoring Tool for Rapid Prototyping of Remapped Interaction in VRRemapping techniques in VR such as repositioning, redirection, and resizing have been extensively studied. Still, interaction designers rarely have the opportunity to use them due to high technical and knowledge barriers. In the paper, we extract common features of 24 existing remapping techniques and develop a high-fidelity immersive authoring tool, namely RemapVR, for rapidly building and experiencing prototypes of remapped space properties in VR that are unperceivable or acceptable to users. RemapVR provides designers with a series of functions for editing remappings and visualizing spatial property changes, mapping relationships between real and virtual worlds, sensory conflicts, etc. Designers can quickly build existing remappings via templates, and author new remappings by interactively recording spatial relations between input trajectory in real world and output trajectory in virtual world. User studies showed that the designs of RemapVR can effectively improve designers' authoring experience and efficiency, and support designers to author remapping prototypes that meet scene requirements and provide good user experience.2025TLTianren Luo et al.Institute of Software, Chinese Academy of Sciences; College of Computer Science and Technology, University of Chinese Academy of SciencesMixed Reality WorkspacesPrototyping & User TestingCHI
Learning from Hybrid Craft: Investigating and Reflecting on Innovating and Enlivening Traditional Craft through Literature ReviewThe key to preserving traditional crafts lies in living transmission, which is inseparable from sustaining artistic production, audience consumption, and progressive innovation with the physical media. As HCI researchers, we focus on the hybrid crafts field, which involves numerous cross-disciplinary integration cases between traditional craftsmanship and digital technology at the physical level, providing inspiration for innovating and enlivening traditional crafts. We conducted a multi-perspective review of 85 hybrid craft articles related to traditional crafts over the past decade, considering aspects such as craft categories, digital technology, target users, and research areas. Through reflection, we propose a design framework for fostering innovation and revitalizing traditional crafts. This paper aims to offer insight into the innovation and enlivenment of traditional crafts through a hybrid craft perspective while also serving as a first review of the hybrid craft field from the traditional craftsmanship perspective.2024GLGuanhong Liu et al.Tongji UniversityShape-Changing Interfaces & Soft Robotic MaterialsTextile Art & Craft DigitizationCHI
Exploring Experience Gaps Between Active and Passive Users During Multi-user Locomotion in VRMulti-user locomotion in VR has grown increasingly common, posing numerous challenges. A key factor contributing to these challenges is the gaps in experience between active and passive users during co-locomotion. Yet, there remains a limited understanding of how and to what extent these experiential gaps manifest in diverse multi-user co-locomotion scenarios. This paper systematically explores the gaps in physiological and psychological experience indicators between active and passive users across various locomotion situations. Such situations include when active users walk, fly by joystick, or teleport, and passive users stand still or look around. We also assess the impact of factors such as sub-locomotion type, speed/teleport-interval, motion sickness susceptibility, etc. Accordingly, we delineate acceptability disparities between active and passive users, offering insights into leveraging notable experimental findings to mitigate discomfort during co-locomotion through avoidance or intervention.2024TLTianren Luo et al.Institute of Software, College of Computer Science and TechnologySocial & Collaborative VRImmersion & Presence ResearchCHI