GestApt: A Pen-Based Interface Integrating Gestures and Recommendations for CAD TasksPen-based interaction interfaces are widely used in precision tasks such as computer-aided design (CAD) modeling. However, frequent mode switching in traditional interfaces often leads to reduced efficiency, while the unstable layout of dynamically adaptive interfaces may cause user discomfort. To address these issues, this paper proposes a novel adaptive pen-based interface, GestApt, which integrates operation recommendation and pen gesture technology to provide an efficient and intuitive interaction method. The core design of GestApt includes a gated recurrent unit (GRU)-based neural network for a predictive toolbar that dynamically forecasts the user’s next action and a convolutional neural network (CNN)-based gesture recognition module to assist with unpredicted operations. To evaluate the effectiveness of GestApt, we conducted a user study with 20 participants performing CAD modeling tasks, comparing their performance with a traditional interface. The results showed that GestApt significantly reduced task completion time while enhancing user experience. Additionally, the optimized toolbar design of GestApt notably reduced the workload on users’ non-dominant hands, helping to alleviate physical fatigue from prolonged interface use. This work demonstrates the advantages of GestApt in improving efficiency, optimizing user interaction, and reducing physical strain, offering a new solution for adaptive design in pen-based interfaces. This design approach not only promotes the development of more efficient and ergonomically friendly interfaces, but also provides a reference for the design of future intelligent CAD interfaces.2026GYGe Yan et al.Zhejiang UniversityHand Gesture RecognitionPrototyping & User TestingCircuit Making & Hardware PrototypingIUI
DuoDrama: Supporting Screenplay Refinement Through LLM-Assisted Human ReflectionAI has been increasingly integrated into screenwriting practice. In refinement, screenwriters expect AI to provide feedback that supports reflection across the internal perspective of characters and the external perspective of the overall story. However, existing AI tools cannot sufficiently coordinate the two perspectives to meet screenwriters' needs. To address this gap, we present DuoDrama, an AI system that generates feedback to assist screenwriters' reflection in refinement. To enable DuoDrama, based on performance theories and a formative study with nine professional screenwriters, we design the Experience-Grounded Feedback Generation Workflow for Human Reflection (ExReflect). In ExReflect, an AI agent adopts an experience role to generate experience and then shifts to an evaluation role to generate feedback based on the experience. A study with fourteen professional screenwriters shows that DuoDrama improves feedback quality and alignment and enhances the effectiveness, depth, and richness of reflection. We conclude by discussing broader implications and future directions.2026YTYuying Tang et al.The Hong Kong University of Science and TechnologyHuman-LLM CollaborationAI-Assisted Creative WritingCreative Collaboration & Feedback SystemsCHI
Rob2HanD: LLM-Driven Robotic Arm for IMU Interaction Dataset GenerationFine-grained hand interaction with Inertial Measurement Unit (IMU) and machine learning offers a low-cost and effective solution. However, the robustness and generalizability of machine learning models are highly dataset-dependent. Existing datasets for interaction design are typically constructed through extensive real user data collection, which limits interaction diversity and personalization. To address these challenges, we propose Rob2HanD, a novel data-generation tool which utilizes large language models (LLMs) to regulate the motion processes of the robotic arm and rapidly constructs IMU datasets. Rob2HanD demonstrates the capability to generate large and usable IMU interaction datasets under few-shot or zero-shot conditions, thereby enhancing the potential for diverse and personalized fine-grained hand interactions. Using a real human dataset, we evaluate machine learning models trained on Rob2HanD-generated data and validate the usability of Rob2HanD. In real-world applications, models trained on Rob2HanD-generated datasets demonstrate strong performance across a variety of customized interaction tasks.2026JLJiangyuan Liu et al.Zhejiang UniversityHand Gesture RecognitionHuman Pose & Activity RecognitionGenerative AI (Text, Image, Music, Video)CHI
Req2CAD: bridging functional requirements and parametric CAD models to support conceptual 3D designConceptual CAD requires transforming functional requirements into parametric 3D models, yet existing systems have steep learning curves and limit creativity through premature fixation. Generative AI shows promise in producing diverse alternatives, while current methods mainly reconstruct CAD modeling sequences of existing designs, making them unsuitable for early stages where ideas are vague and intent is difficult to express. We present Req2CAD, an interactive system that enables designers to progress from design problems toward conceptual CAD models through functional decomposition, function–structure reasoning, and component-level CAD creation and iteration. Req2CAD introduces a data annotation pipeline that maps functional requirements to the 3D structural design space, a dual-feature CAD representation to support design space exploration and CAD ideation, and a progressive CAD generation method that enables rapid CAD model creation through multi-modal intent expression. A technical evaluation and user study demonstrate the effectiveness of Req2CAD, highlighting its potential for human–AI co-creation.2026QJQianzhi Jing et al.Zhejiang UniversityCreative Coding & Computational ArtPrototyping & User TestingComputational Methods in HCICHI
Y-zipper: 3D Printing Flexible–Rigid Transition Mechanism for Rapid and Reversible AssemblyWe present Y-zipper, a novel three-sided 3D-printed zipper structure that enables three flexible strips to interlock and transform into a rigid rod-like form. Building on this flex–rigid transition mechanism, we further design a specialized slider to achieve rapid and reversible zipping interactions. This slider serves as the basis for three actuation methods—manual, dynamic mechanical, and static mechanical—which enable both remote control and automated closure and release. In addition, Y-zipper provides four motion primitives: straight, bend, coil, and screw, whose combinations extend the flex–rigid transition mechanism to spatial curve structures. To support customization, we develop a computational design tool that automatically generates zipper geometry based on input primitives, unfolds the structure for 3D printing, and embeds both teeth and compliant bridges. Controlled experiments evaluate its mechanical properties, repeatability, and actuation speed, demonstrating robustness and reliability. Finally, we showcase a series of functional prototypes, including a medical wrist brace, a kinetic art installation, and a rapidly deployable tent structure.2026JLJiaji Li et al.MITShape-Changing Interfaces & Soft Robotic MaterialsCircuit Making & Hardware PrototypingCustomizable & Personalized ObjectsCHI
Xspine: Integrating Motion Sensing Capability into Dynamic Structures Using Multi-material FDM 3D PrintingWe present Xspine, a design and fabrication method for creating motion-capable, self-sensing structures using multi-material FDM 3D printing with conductive filaments. Our method embeds compliant mechanisms and circuits directly into geometries, enabling the detection of large deformations in a single, assembly-free print. Specifically, we design printable components and circuit layouts aligned with the layer-by-layer nature of FDM 3D printing. Furthermore, we explore physical and digital augmentation strategies to enhance the interactive potential of the structures. To simplify the workflow, we develop an interactive design tool that allows users to configure motion behaviors, preview structural responses, and generate printable circuits. Finally, we demonstrate several application examples that highlight the potential of Xspine for customizable and interactive 3D-printed devices.2026MLMingming Li et al.Zhejiang UniversityShape-Changing Interfaces & Soft Robotic MaterialsCircuit Making & Hardware PrototypingCustomizable & Personalized ObjectsCHI
GuideMe: A VLM-Based System Assisting Independent Smartphone Learning for Older AdultsDue to age-related cognitive and physical decline, older adults face numerous difficulties when learning new functions of smartphone applications. However, older adults often struggle to ask questions clearly and follow instructions independently. Through a formative study (N=16), we identified the behaviors and challenges of older adults seeking help independently and analyzed the effective mechanism of in-person instruction. Based on these findings, we proposed GuideMe, an in-situ conversational instruction system for older adults' application learning. GuideMe utilizes Vision-Language-Models to analyze multimodal context in users' situations, then assists users in confirming their intentions by asking clarifying questions, and finally provides step-by-step instructions using in-situ highlight and deictic gestures. We conducted a user study (N=18) that demonstrated that GuideMe significantly reduced users' cognitive load during learning, helped them ask questions and follow instructions efficiently, and achieved performance comparable to that of in-person instruction.2026KFKairong FANG et al.The Hong Kong University of Science and Technology (Guangzhou)Aging-Friendly Technology DesignHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationCHI
Take the Dog to the Park: Quadruped Robot for Joint Attention Training with Autistic Children in Naturalistic SettingsRobot-supported interventions for joint attention (JA) in autistic children have shown encouraging outcomes, yet most remain confined to stationary robots in indoor settings, limiting opportunities for skill generalization and broader developmental benefits. We introduce an intervention that employs a quadruped robot dog as a peer-like partner for JA training across both indoor and outdoor environments. In this intervention, the robot dog directs children's attention to distributed targets in the environment and initiates JA trials. A four-week pre-post exploratory study with six autistic children demonstrated improvements in JA performance and indications of transfer to daily social communication. Spontaneous behaviors such as motor imitation (crawling) and novel social interactions with the robot also emerged, suggesting potential for broader developmental gains. These findings provide initial evidence for the efficacy of mobile robot-supported JA interventions in naturalistic contexts and offer implications for future design.2026YFYuyang Fang et al.Zhejiang UniversityRobots in Education & HealthcareCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Special Education TechnologyCHI
Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training FrameworkChart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are reliable but tedious, and mixed-initiative systems, while more efficient, lack generalizability. Recent multimodal large language models (MLLMs) offer a unified interface for chart interpretation, yet their ability to extract accurate data tables, especially without visible labels, remains unclear. We build a benchmark featuring diverse real-world charts without data labels to evaluate this capability. Results show that, while current MLLMs reliably reconstruct table structures, they struggle with precise value recovery. To address this, we revisit chart data extraction from a human-centered perspective and argue that extraction should follow a progressive learning process similar to how people read charts. Our training framework substantially improves numerical accuracy, achieving state-of-the-art performance with a 7B-parameter model. A user study further shows that our model effectively supports mixed-initiative workflows for reliable chart data extraction.2026YHYuchen He et al.Zhejiang UniversityGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationInteractive Data VisualizationCHI
Cerebra: Aligning Implicit Knowledge in Interactive SQL AuthoringLLM-driven tools have significantly lowered barriers to writing SQL queries. However, user instructions are often underspecified, assuming the model understands implicit knowledge, such as dataset schemas, domain conventions, and task-specific requirements, that isn't explicitly provided. This results in frequently erroneous scripts that require users to repeatedly clarify their intent. Additionally, users struggle to validate generated scripts because they cannot verify whether the model correctly applied implicit knowledge. We present Cerebra, an interactive NL-to-SQL tool that aligns implicit knowledge between users and LLMs during SQL authoring. Cerebra automatically retrieves implicit knowledge from historical SQL scripts based on user instructions, presents this knowledge in an interactive tree view for code review, and supports iterative refinement to improve generated scripts. To evaluate the effectiveness and usability of Cerebra, we conducted a user study with 16 participants, demonstrating its improved support for customized SQL authoring. The source code of Cerebra is available at https://github.com/zjuidg/CHI26-Cerebra.2026YZYunfan Zhou et al.Zhejiang UniversityHuman-LLM CollaborationExplainable AI (XAI)Computational Methods in HCICHI
WeavePrint: A Generative Method for Woven-like Additive Manufacturing Based on Parametric Weave StructuresThis paper presents WeavePrint, a parametric and multi-material additive manufacturing method for woven-like structures. By fusing traditional weaving logic with computational generation, WeavePrint overcomes limitations in pattern programmability, mechanical tunability, and build size. A parametric generator creates plain, twill, satin, and image-based jacquard patterns, while supporting curved-surface mapping and continuous vertical roll-to-roll printing for scalable production. Systematic tensile and compression tests quantify how overlap length, filament width, and multi-material combinations influence inter-layer adhesion and global mechanics. We define four motion primitives: bending, twisting, curved extension-contraction, and hinged extension-contraction, implemented through straight, diagonal, and curved weaves to produce predictable deformations. Demonstrations in wearable supports, robotic components, and rehabilitation devices highlight its broad potential in human-computer interaction. By unifying parametric modeling with multi-material continuous fabrication, WeavePrint provides a scalable route to programmable, anisotropic, and dynamically responsive interactive fabrics.2026JCJiacheng Cao et al.Zhejiang UniversityShape-Changing Interfaces & Soft Robotic MaterialsShape-Changing Materials & 4D PrintingCustomizable & Personalized ObjectsCHI
Visualizing Tree-of-analysis: Facilitating Conversational Visual Analytics for NovicesConversational visual analytics (CVA) make data exploration accessible to novices but often leave users disoriented during multi-turn conversations. Previous approaches provide data-centric recommendations, but fail to help users regain orientations. To bridge this gap, we conducted a formative study (N=12) revealing that novices are insensitive to analytical cues and rely on vague queries, leading to disorientation and task failures. In contrast, experts are sensitive to two types of analytical cues and use seven types of queries to organize workflows. Based on these findings, we propose ToA, a novel approach that structures the CVA process as an interactive analysis tree. Moreover, we visualize this tree, with AI outputs as nodes (containing two cue types) and user queries as edges (categorized by seven query types), to provide novices with an overview of their analysis journey. We evaluated ToA through user studies (N=12) and expert interviews (N=3). The results suggest that ToA eliminates task failure and increases per-turn insights (+58.3%), despite longer per-turn thinking time (+17.7%). Expert interviews further confirm its potential to democratize visual analytics.2026FQFeiyuan Qu et al.Zhejiang UniversityInteractive Data VisualizationExploratory Search & Information SeekingExplainable AI (XAI)CHI
MusicScaffold: Bridging Machine Efficiency and Human Growth in Adolescent Creative Education through Generative AIAdolescence is marked by strong creative impulses but limited strategies for structured expression, often leading to frustration or disengagement. While generative AI lowers technical barriers and delivers efficient outputs, its role in fostering adolescents’ expressive growth has been overlooked. We propose MusicScaffold, an adolescent-centered framework that transforms classical AI roles from broad conceptualizations into stage-specific, actionable developmental scaffolds designed to make expressive strategies transparent and learnable and to support adolescents in mastering creative expression. In a four-week study with middle school students (ages 12–14), MusicScaffold enhanced cognitive specificity, behavioral regulation, and affective autonomy in music creation. By reframing generative AI as a scaffold rather than a generator, this work bridges the machine efficiency of generative systems with human growth in adolescent creativity education.2026ZHzhejing hu et al.The Hong Kong Polytechnic UniversityGenerative AI (Text, Image, Music, Video)Programming Education & Computational ThinkingEarly Childhood Education TechnologyCHI
SootheMind: Exploring Body-Site-Specific Vibrotactile and Thermatactile Stimuli for Music-guided Emotion ModulationMusical emotion modulation is central to mental well-being, yet existing affective haptic systems often prioritize technical feasibility over investigation of where and what optimal stimuli should be applied. This paper systematically examines the emotional effects of vibrotactile, thermotactile, and combined stimuli based on the Valence–Arousal model across the wrist, neck, and ear under two music conditions, indexed by EEG measures and subjective ratings. We found that both body site and stimulus type significantly influenced emotional responses. The ear strongly enhanced arousal, the neck produced context-dependent effects, and the wrist primarily modulated pleasantness. Vibration primarily boosted arousal, thermal cues enhanced valence, and their combination enabled a more balanced, immersive experience. Our findings provide scientific guidance for future affective wearable design in various contexts.2026KWKun Wang et al.College of Computer Science and Technology, Zhejiang UniversityVibrotactile Feedback & Skin StimulationHaptic WearablesEmotion-Sensing WearablesCHI
NoteFlow: Leveraging Charts as Sight Glasses for Consistent and Continuous Data Flow TracingComputational notebooks offer a flexible environment for exploratory data analysis (EDA), but this flexibility often leads to disorganized and iterative execution of notebook cells, making it difficult to track how data states evolve. Consequently, data scientists must devote extra mental effort to staying aware of data states, which is both tedious and prone to overlooking anomalies. To address this challenge, we developed NoteFlow, a notebook extension that leverages charts as ``sight glasses'' to provide a consistent and continuous tracing of data flow. NoteFlow allows users to (1) validate various facets of the current data state using recommended charts provided immediately after each cell execution, and (2) trace the global evolution of selected charts to continuously observe how particular data attributes evolve throughout the EDA process. We evaluated NoteFlow's effectiveness through a controlled study with 12 participants and a one-month field study with 2 data scientists on real-world workflows.2026YTYuan Tian et al.Zhejiang UniversityInteractive Data VisualizationData-Driven Personal Decision-MakingUser Research Methods (Interviews, Surveys, Observation)CHI
HyperMOOC: Augmenting MOOC Videos with Concept-based Embedded VisualizationsMassive Open Online Courses (MOOCs) have become increasingly popular worldwide. However, learners primarily rely on watching videos, easily losing knowledge context and reducing learning effectiveness. We propose HyperMOOC, a novel approach augmenting MOOC videos with concept-based embedded visualizations to help learners maintain knowledge context. Informed by expert interviews and literature review, HyperMOOC employs multi-glyph designs for different knowledge types and multi-stage interactions for deeper understanding. Using a timeline-based radial visualization, learners can grasp cognitive paths of concepts and navigate courses through hyperlink-based interactions. We evaluated HyperMOOC through a user study with 36 MOOC learners and interviews with two instructors. Results demonstrate that HyperMOOC enhances learners' learning effect and efficiency on MOOCs, with participants showing higher satisfaction and improved course understanding compared to traditional video-based learning approaches.2026LYLi Ye et al.Hangzhou Dianzi UniversityInteractive Data VisualizationOnline Learning & MOOC PlatformsIntelligent Tutoring Systems & Learning AnalyticsCHI
CritiqueCrew: Orchestrating Multi-Perspective Conversational Design CritiqueUI designers face growing cognitive load and cross-functional friction at the intersection of user needs, business goals, and engineering constraints. Existing automated tools often deliver static "problem lists," lacking actionable repair paths and disrupting creative flow. We introduce CritiqueCrew, a Figma tool that supports designers through conversational critique. CritiqueCrew generates multi-faceted insights by implementing a multi-perspective orchestration of distinct expert roles (UX, PM, Engineer). It translates abstract critiques into concrete actions via in-context feedback and interactive remediation. Across two independent controlled studies (Total N=48), CritiqueCrew significantly improved both design quality and subjective experience compared to a traditional static checker. Furthermore, our results confirm that the structured orchestration of expert roles—rather than a unified model—is key to fostering trust and creativity support. Our work demonstrates how AI can shift from a "problem auditor" to a "solution co-creator" by integrating multi-perspective dialogue with interactive repair, offering design implications for future creative tools.2026XCXiaojiao Chen et al.Zhejiang UniversityCreative Collaboration & Feedback SystemsPrototyping & User TestingGenerative AI (Text, Image, Music, Video)CHI
PoemPalette: Facilitating Poetry Creative Exploration and Foundational Understanding through the Ideorealm Alignment of Paintings and PoemsThe “Ideorealm Alignment of Paintings and Poems (IA-PP)” theory rooted in Chinese classical aesthetics offers a perspective for exploring poetry’s deep connotations. This study presents PoemPalette, a novel IA-PP creative-exploration tool that integrates generative AI to guide poetry enthusiasts in actively constructing an ideorealm for the poetic painting they envision, informed by a formative study with six experts. We extract the core symbols of poetry, transform them into Scene Graph (SG), and generate images for users to freely compose, enabling IA-PP creative exploration. The system incorporates Large Language Model (LLM) agents to enhance the foundational understanding of poetry. In a controlled experiment on Chinese poetry and Japanese haiku with 60 participants, we analyze which interaction mechanisms most contribute to foundational understanding and creative outcomes, compared with both AI and non-AI baselines. Situated within East Asian poetry traditions, this study introduces cultural theories to guide the design of AI co-creation tools, using a graph-based interface of interpretable intermediate representations.2026YZYing Zhang et al.Zhejiang UniversityGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationCreative Collaboration & Feedback SystemsCHI
RECALLbot: Designing Agentic Memory and Reciprocal Disclosure for Human–Chatbot RelationshipsSocial chatbots are increasingly studied for their benefits in providing companionship and emotional support. These benefits rely on forming human-chatbot relationships that require credible social identity and reciprocal interaction. Memory plays a dual role: it strengthens social identity by enabling the chatbot to remember, and supports reciprocal interaction when memories are disclosed mutually. We present RECALLbot, an LLM-driven social chatbot that constructs agentic memories, including life-like Me Memory and co-constructed We Memory, and adaptively applies reciprocal disclosure strategies with user controls. In a two-week between-subjects study (N = 40), RECALLbot was compared with a baseline system lacking agentic memories and reciprocal disclosure strategies. Results show that RECALLbot enhanced perceptions of the chatbot’s social identity, elicited more frequent and deeper self-disclosures, and fostered greater trust.2026ZJZhaojun Jiang et al.Zhejiang UniversityIntelligent Voice Assistants (Alexa, Siri, etc.)Agent Personality & AnthropomorphismAffective Human-Computer DialogueCHI
The Privacy Paradox of LLMs: User Perceptions and the Reality of PII LeakageLarge language models (LLMs) are increasingly deployed, yet they introduce significant privacy risks by disclosing personally identifiable information (PII) during interactions. Although prior work has demonstrated the feasibility of extracting PII from LLMs, no comprehensive study has evaluated the actual extent of PII leakage across mainstream LLMs or investigated user perceptions, literacy, and behavioral responses to these risks. To address these gaps, we conduct a large-scale evaluation of PII leakage in popular LLMs, demonstrating that attackers can extract email addresses and phone numbers with high success rates. Through a mixed-methods study involving 20 interviews and 204 survey participants, we identify significant discrepancies between user concerns and behavior: despite strong concerns about PII leakage and limited understanding of training data provenance, users continue to use LLMs due to perceived utility, often exhibiting privacy cynicism. Based on these findings, we propose design implications for enhancing the privacy-utility balance in future LLM deployments.2026SCShuai Cheng et al.Zhejiang UniversityExplainable AI (XAI)Privacy by Design & User ControlPrivacy Perception & Decision-MakingCHI