A Multi-Factorial Comparative Analysis of Perceived Privacy Violations Caused by Smart Speakers in Germany and the UKSmart speakers pose privacy risks to users and bystanders. We do not know how these risks are perceived depending on different factors, such as the potential privacy violators, the nature of the privacy violation, the different user groups, and culture. Understanding these perceptions is crucial to providing adequate privacy solutions and legislation. To this end, 1,768 participants from Germany and the UK answered our online-questionnaire about their perceptions of five different actors’ possibilities, intentions, and legal bases to commit five privacy violations: data access, data inference, overhearing conversations, secondary use, and passing data along. Participants expressed mild concerns about the main user but greater worry about manufacturers and the state. We observe growing concern among younger people, especially in the UK and that users who do not own the smart speaker are the least concerned group. Our approach can be used to better differentiate perceptions of concerns in other contexts.2025PKPatrick Kühtreiber et al.Privacy by Design & User ControlPrivacy Perception & Decision-MakingIoT Device PrivacyCHI
ShoeGenAI: A Creativity Support Tool Bridging Design Intention and Feasibility in Shoe DesignProduct designers increasingly turn to generative AI for creating concept images, but these outputs often fall short in terms of real-world manufacturability and typically require iterative revisions to align with intended designs. Concentrating on sneaker design, we introduce ShoeGenAI, an AI tool that enhances designers' creativity while ensuring feasible outcomes and reducing the need for post-processing. A formative study involving four shoe designers uncovered key limitations in both traditional workflows and current genereative AI tools. These insights guided the development of four core features: fine-tuned models trained on domain-specific data, template-driven prompt assistance, support for hybrid part recombination, and localized editing for detail refinement. A subsequent user study with 20 designers showed that ShoeGenAI enabled clearer communication of design intent, more efficient workflows with less manual correction, and higher satisfaction with the realism and feasibility of the generated outputs. We also explore how professionals and novices differ in their use of creativity support tools, especially across tasks ranging from imitation to original creation.2025HKHui-Jun Kim et al.Generative AI (Text, Image, Music, Video)Creative Collaboration & Feedback SystemsCustomizable & Personalized ObjectsCHI
Why am I seeing this: Democratizing End User Auditing for Online Content RecommendationsPersonalized recommendation systems tailor content based on user attributes, which are either provided or inferred from private data. Research suggests that users often hypothesize about reasons behind contents they encounter (e.g., ``I see this jewelry ad because I am a woman''), but they lack the means to confirm these hypotheses due to the opaqueness of these systems. This hinders informed decision-making about privacy and system use and contributes to the lack of algorithmic accountability. To address these challenges, we introduce a new interactive sandbox approach. This approach creates sets of synthetic user personas and corresponding personal data that embody realistic variations in personal attributes, allowing users to test their hypotheses by observing how a website's algorithms respond to these personas. We tested the sandbox in the context of targeted advertisement. Our user study demonstrates its usability, usefulness, and effectiveness in empowering end-user auditing in a case study of targeting ads.2025CCChaoran Chen et al.Explainable AI (XAI)AI Ethics, Fairness & AccountabilityAlgorithmic Transparency & AuditabilityCHI
MEDebiaser: A Human-AI Feedback System for Mitigating Bias in Multi-label Medical Image ClassificationMedical images often contain multiple labels with imbalanced distributions and co-occurrence, leading to bias in multi-label medical image classification. Close collaboration between medical professionals and machine learning practitioners has significantly advanced medical image analysis. However, traditional collaboration modes struggle to facilitate effective feedback between physicians and AI models, as integrating medical expertise into the training process via engineers can be time-consuming and labor-intensive. To bridge this gap, we introduce MEDebiaser, an interactive system enabling physicians to directly refine AI models using local explanations. By combining prediction with attention loss functions and employing a customized ranking strategy to alleviate scalability, MEDebiaser allows physicians to mitigate biases without technical expertise, reducing reliance on engineers, and thus enhancing more direct human-AI feedback. Our mechanism and user studies demonstrate that it effectively reduces biases, improves usability, and enhances collaboration efficiency, providing a practical solution for integrating medical expertise into AI-driven healthcare.2025SSShaohan Shi et al.Brain-Computer Interface (BCI) & NeurofeedbackExplainable AI (XAI)AI-Assisted Decision-Making & AutomationCHI
CoGrader: Transforming Instructors' Assessment of Project Reports through Collaborative LLM IntegrationGrading project reports are increasingly significant in today’s educational landscape, where they serve as key assessments of students' comprehensive problem-solving abilities. However, it remains challenging due to the multifaceted evaluation criteria involved, such as creativity and peer-comparative achievement. Meanwhile, instructors often struggle to maintain fairness throughout the time-consuming grading process. Recent advances in AI, particularly large language models, have demonstrated potential for automating simpler grading tasks, such as assessing quizzes or basic writing quality. However, these tools often fall short when it comes to complex metrics, like design innovation and the practical application of knowledge, that require an instructor’s educational insights into the class situation. To address this challenge, we conducted a formative study with six instructors and developed CoGrader, which introduces a novel grading workflow combining human-LLM collaborative metrics design, benchmarking, and AI-assisted feedback. CoGrader was found effective in improving grading efficiency and consistency while providing reliable peer-comparative feedback to students. We also discuss design insights and ethical considerations for the development of human-AI collaborative grading systems.2025ZCZixin Chen et al.Human-LLM CollaborationIntelligent Tutoring Systems & Learning AnalyticsSTEM Education & Science CommunicationCHI
MorphingSkin: A Skin-like Platform that Integrates Multimodal Hydraulic Actuators Based on Flexible Electroosmotic PumpsInteractive surfaces have garnered significant attention in Human-Computer Interaction, with fluid-driven actuators being a promising actuation technology due to their flexible form factors and multimodal interactivities. However, traditional fluid-driven systems typically rely on bulky and noisy electromechanical hardware, limiting their portability and practicality. While recent work has introduced compact hydraulic actuators like electroosmotic pumps (EOPs) in haptic devices, their potential for building multifunctional interactive surfaces remains largely unexplored. In this work, we present MorphingSkin, a skin-like platform that integrates multiple, multimodal hydraulic actuators using flexible EOPs as lightweight and self-contained fluidic actuators. We introduce the architecture of MorphingSkin and its versatile design space for multimodal actuation in force, shape, optical, and weight domains. We demonstrate interactive and robotic applications that integrate multiple actuators working collectively within a single MorphingSkin device. Through this work, we envision the future of using MorphingSkin technology for interactive surfaces that integrate flexible form factors and multimodal actuation capabilities.2025TYTianyu Yu et al.Haptic WearablesShape-Changing Interfaces & Soft Robotic MaterialsCHI
SketchGPT: A Sketch-based Multimodal Interface for Application-Agnostic LLM InteractionHuman interaction with large language models (LLMs) is typically confined to text or image interfaces. Sketches offer a powerful medium for articulating creative ideas and user intentions, yet their potential remains underexplored. We propose SketchGPT, a novel interaction paradigm that integrates sketch and speech input directly over the system interface, facilitating open-ended, context-aware communication with LLMs. By leveraging the complementary strengths of multimodal inputs, expressions are enriched with semantic scope while maintaining efficiency. Interpreting user intentions across diverse contexts and modalities remains a key challenge. To address this, we developed a prototype based on a multi-agent framework that infers user intentions within context and generates executable context-sensitive and toolkit-aware feedback. Using Chain-of-Thought techniques for temporal and semantic alignment, the system understands multimodal intentions and performs operations following human-in-the-loop confirmation to ensure reliability. User studies demonstrate that SketchGPT significantly outperforms unimodal manipulation approaches, offering more intuitive and effective means to interact with LLMs.2025ZHZeyuan Huang et al.Voice User Interface (VUI) DesignHuman-LLM CollaborationCHI
L.ink: Procedural Ink Growth for Controllable SurpriseControl, a common principle in interface design, helps artists achieve desired outcomes when using creativity support tools. However, surprise also plays a role in creative practice by facilitating introspection and adaptation. Consequently, creativity support tools face the challenge of balancing these two properties. We present L.ink, a digital illustration tool that empowers artists to draw with controllable yet unpredictable procedural growth styles powered by L-systems. Through a formative study of an early prototype of the system, we identify three types of surprise and adapt our design with a direct-manipulation editing interface with live visual feedback and a hand-drawn stamp tool to afford control and mitigate unwanted surprise. We further evaluate how controllable surprise impacts creative workflow and experience through a task-based study with 12 artists. Based on our observations, we extract guidelines for when and how to effectively incorporate unpredictability into creativity support tools.2025ECEric Nai-Li Chen et al.Graphic Design & Typography ToolsCustomizable & Personalized ObjectsKnowledge Worker Tools & WorkflowsCHI
PosterMate: Audience-driven Collaborative Persona Agents for Poster DesignPoster designing can benefit from synchronous feedback from target audiences. However, gathering audiences with diverse perspectives and reconciling them on design edits can be challenging. Recent generative AI models present opportunities to simulate human-like interactions, but it is unclear how they may be used for feedback processes in design. We introduce PosterMate, a poster design assistant that facilitates collaboration by creating audience-driven persona agents constructed from marketing documents. PosterMate gathers feedback from each persona agent regarding poster components, and stimulates discussion with the help of a moderator to reach a conclusion. These agreed-upon edits can then be directly integrated into the poster design. Through our user study (N=12), we identified the potential of PosterMate to capture overlooked viewpoints, while serving as an effective prototyping tool. Additionally, our controlled online evaluation (N=100) revealed that the feedback from an individual persona agent is appropriate given its persona identity, and the discussion effectively synthesizes the different persona agents' perspectives.2025DSDonghoon Shin et al.AI-Assisted Creative WritingCreative Collaboration & Feedback SystemsCHI
VIP-Sim: A User-Centered Approach to Vision Impairment Simulation for Accessible DesignPeople with vision impairments (VIPs) often rely on their remaining vision when interacting with user interfaces. Simulating visual impairments is an effective tool for designers, fostering awareness of the challenges faced by VIPs. While previous research has introduced various vision impairment simulators, none have yet been developed with the direct involvement of VIPs or thoroughly evaluated from their perspective. To address this gap, we developed VIP-Sim. This symptom-based vision simulator was created through a participatory design process tailored explicitly for this purpose, involving N=7 VIPs. 21 symptoms, like field loss or light sensitivity, can be overlaid on desktop design tools. Most participants felt VIP-Sim could replicate their symptoms. VIP-Sim was received positively, but concerns about exclusion in design and comprehensiveness of the simulation remain, mainly whether it represents the experiences of other VIPs.2025MRMax Rädler et al.Visual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)Universal & Inclusive DesignParticipatory DesignCHI
NarraGuide: an LLM-based Narrative Mobile Robot for Remote Place ExplorationRobotic telepresence enables users to navigate and experience remote environments. However, effective navigation and situational awareness depend on users’ prior knowledge of the environment, limiting the usefulness of these systems for exploring unfamiliar places. We explore how integrating location-aware LLM-based narrative capabilities into a mobile robot can support remote exploration. We developed a prototype system, called NarraGuide, that provides narrative guidance for users to explore and learn about a remote place through a dialogue-based interface. We deployed our prototype in a geology museum, where remote participants (𝑛 = 20) used the robot to tour the museum. Our findings reveal how users perceived the robot’s role, engaged in dialogue in the tour, and expressed preferences for bystander encountering. Our work demonstrates the potential of LLM-enabled robotic capabilities to deliver location-aware narrative guidance and enrich the experience of exploring remote environments.2025YHYaxin Hu et al.Social & Collaborative VRAR Navigation & Context AwarenessTeleoperation & TelepresenceCHI
StepWrite: Adaptive Planning for Speech-Driven Text GenerationPeople frequently use speech-to-text systems to compose short texts with voice. However, current voice-based interfaces struggle to support composing more detailed, contextually complex texts, especially in scenarios where users are on the move and cannot visually track progress. Longer-form communication, such as composing structured emails or thoughtful responses, requires persistent context tracking, structured guidance, and adaptability to evolving user intentions---capabilities that conventional dictation tools and voice assistants do not support. We introduce StepWrite, a large language model-driven voice-based interaction system that augments human writing ability by enabling structured, hands-free and eyes-free composition of longer-form texts while on the move. StepWrite decomposes the writing process into manageable subtasks and sequentially guides users with contextually-aware non-visual audio prompts. StepWrite reduces cognitive load by offloading the context-tracking and adaptive planning tasks to the models. Unlike baseline methods like standard dictation features (e.g., Microsoft Word) and conversational voice assistants (e.g., ChatGPT Advanced Voice Mode), StepWrite dynamically adapts its prompts based on the evolving context and user intent, and provides coherent guidance without compromising user autonomy. An empirical evaluation with 25 participants engaging in mobile or stationary hands-occupied activities demonstrated that StepWrite significantly reduces cognitive load, improves usability and user satisfaction compared to baseline methods. Technical evaluations further confirmed StepWrite's capability in dynamic contextual prompt generation, accurate tone alignment, and effective fact checking. This work highlights the potential of structured, context-aware voice interactions in enhancing hands-free and eye-free communication in everyday multitasking scenarios.2025HAHamza El Alaoui et al.Voice User Interface (VUI) DesignHuman-LLM CollaborationCHI
NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding ModificationConversational LLMs have been widely adopted by domain users with limited programming experience to solve domain problems. However, these users often face misalignment between their intent and generated code, resulting in frustration and rounds of clarification. This work first investigates the cause of this misalignment, which dues to bidirectional ambiguity: both user intents and coding tasks are inherently nonlinear, yet must be expressed and interpreted through linear prompts and code sequences. To address this, we propose direct intent–task matching, a new human–LLM interaction paradigm that externalizes and enables direct manipulation of the LLM understanding, i.e., the coding tasks and their relationships inferred by the LLM prior to code generation. As a proof-of-concept, this paradigm is then implemented in NeuroSync, which employs a knowledge distillation pipeline to extract LLM understanding, user intents, and their mappings, and enhances the alignment by allowing users to intuitively inspect and edit them via visualizations. We evaluate the algorithmic components of NeuroSync via technical experiments, and assess its overall usability and effectiveness via a user study (N=12). The results show that it enhances intent–task alignment, lowers cognitive effort, and improves coding efficiency.2025WZWenshuo ZHANG et al.Human-LLM CollaborationExplainable AI (XAI)CHI
Preference-Guided Multi-Objective UI Adaptation3D Mixed Reality interfaces have nearly unlimited space for layout placement, making automatic UI adaptation crucial for enhancing the user experience. Such adaptation is often formulated as a multi-objective optimization (MOO) problem, where multiple, potentially conflicting design objectives must be balanced. However, selecting a final layout is challenging since MOO typically yields a set of trade-offs along a Pareto frontier. Prior approaches often required users to manually explore and evaluate these trade-offs, a time-consuming process that disrupts the fluidity of interaction. To eliminate this manual and laborous step, we propose a novel optimization approach that efficiently determines user preferences from a minimal number of UI element adjustments. These determined rankings are translated into priority levels, which then drive our priority-based MOO algorithm. By focusing the search on user-preferred solutions, our method not only identifies UIs that are more aligned with user preferences, but also automatically selects the final design from the Pareto frontier; ultimately, it minimizes user effort while ensuring personalized layouts. Our user study in a Mixed Reality setting demonstrates that our preference-guided approach significantly reduces manual adjustments compared to traditional methods, including fully manual design and exhaustive Pareto front searches, while maintaining high user satisfaction. We believe this work opens the door for more efficient MOO by seamlessly incorporating user preferences.2025YSChristoph Gebhardt et al.Mixed Reality WorkspacesHuman-LLM CollaborationCHI
SwitchAR: Perceptual Manipulations in Augmented RealityPerceptual manipulations (PMs) like redirected walking (RDW) are frequently applied in Virtual Reality (VR) to overcome technological limitations. These PMs manipulate the user’s visual perceptions (e.g. through rotational gains), which is currently challenging in Augmented Reality (AR). We propose SwitchAR, a PM for video pass-through AR leveraging change and inattentional blindness to imperceptibly switch between the camera stream of the real environment and a 3D reconstruction. This enables perceptual manipulations in what users still perceive as AR. We present our pipeline consisting of (1) Reconstruction, (2) Switch (AR -> VR), (3) PM and (4) Switch (VR -> AR), and discuss its challenges and our solutions. In a user study (n=20), we found that no participant noticed the switch and only one the PM. Additionally, despite revealing that a manipulation happened, participants could not detect the switch in a consecutive run. SwitchAR is a fundamental basis enabling AR PMs.2025JWJonas Wombacher et al.AR Navigation & Context AwarenessImmersion & Presence ResearchCHI
Move with Style! Enhancing Avatar Embodiment in Virtual Reality through Proprioceptive Motion FeedbackIn virtual reality (VR), users slip into a variety of roles, represented by a rich diversity of avatars that each exhibit specific visual attributes and motion styles. While users can see their avatar's motion in VR, they usually cannot feel it. To enhance avatar embodiment, we propose active proprioceptive feedback that aligns users' physical movements with the expected motion style of their avatar, for instance, by mimicking the avatar's weight, typical motion speed or motion range. We introduce a conceptual space of relevant motion properties which enable designers to create expressive proprioceptive motion styles for avatars. We instantiate this concept with MotionStyler: a system for designing customized motion styles and rendering them in real-time with an arm-based exoskeleton that is synchronized with the VR avatar. Results from a survey confirmed the expressiveness of the proposed conceptual space. A user study demonstrated the system's capability to create diverse proprioceptive motion styles which enhance user's self-identification with their avatar and thereby positively contribute to avatar embodiment in VR.2025DWDavid Wagmann et al.Force Feedback & Pseudo-Haptic WeightIdentity & Avatars in XRCHI
Graffiti: Enabling an Ecosystem of Personalized and Interoperable Social ApplicationsMost social applications, from Twitter to Wikipedia, have rigid one-size-fits-all designs, but building new social applications is both technically challenging and results in applications that are siloed away from existing communities. We present Graffiti, a system that can be used to build a wide variety of personalized social applications with relative ease that also interoperate with each other. People can freely move between a plurality of designs—each with its own aesthetic, feature set, and moderation—all without losing their friends or data. Our concept of total reification makes it possible for seemingly contradictory designs, including conflicting moderation rules, to interoperate. Conversely, our concept of channels prevents interoperation from occurring by accident, avoiding context collapse. Graffiti applications interact through a minimal client-side API, which we show admits at least two decentralized implementations. Above the API, we built a Vue.js plugin, which we use to develop applications similar to Twitter, Messenger, and Wikipedia using only client-side code. Our case studies explore how these and other novel applications interoperate, as well as the broader ecosystem that Graffiti enables.2025THTheia Henderson et al.Social Platform Design & User BehaviorGig Economy PlatformsSmart Home Interaction DesignCHI
Sculpin: Direct-Manipulation Transformation of JSONMany end-user programming tasks require programmatically processing JSON, wrangling it from one format to another or building interactive applications atop it. But end-users are impeded by the indirectness and steep learning curve of textual code. We present Sculpin, a direct-manipulation environment supporting a broad range of JSON-transformation tasks. A user of Sculpin transforms JSON data step by step, recording a program in the process. Sculpin makes three design commitments to ensure directness and versatility: (1) steps are small and precise, not inferred; (2) steps are general-purpose and open to re-appropriation; (3) steps operate on JSON itself, rather than on a limited intermediate representation. To support these commitments, Sculpin introduces a mechanism of sculptable selections: the user can direct their action by guiding a selection on top of the data through small steps like generalization and hierarchical navigation. Sculpin also extends JSON with embedded interface elements like form inputs and buttons, allowing applications to be sculpted incrementally from source data. We demonstrate the breadth and directness of Sculpin in use-cases ranging from wrangling data to building applications. We evaluate Sculpin through a heuristic analysis, situating it in a broad space of programming systems and surfacing limitations such as difficulties editing preexisting programs.2025JHJoshua Horowitz et al.Knowledge Worker Tools & WorkflowsPrototyping & User TestingCHI
UltraEdit: In-Situ Design Environment for Ultrasound HaptizationWe present UltraEdit, an in-situ design environment that enables users to directly edit ultrasound haptic sensations in VR using barehand interactions. UltraEdit represents haptic sensations as tangible objects, called blobs, which users can modify or apply to 3D objects through intuitive hand gestures. Users can create, edit, copy, and apply blobs, allowing them to work with multiple haptic sensations to design virtual objects with diverse tactile feedback. Additionally, UltraEdit allows users to create spatial and temporal haptic patterns using time blobs and spatial drawing features. Users can draw custom-shaped haptic patterns directly on their hands, adapting to comprehensive design scenarios. To evaluate UltraEdit, we conducted an exploratory user study assessing its usability, effectiveness, and ease of learning. We also compared its performance to an existing desktop-based haptic editing tool. Participants found UltraEdit intuitive to learn, enjoyable to use, and effective for adding haptic feedback to virtual objects.2025RNRichard Huynh Noeske et al.Mid-Air Haptics (Ultrasonic)Shape-Changing Interfaces & Soft Robotic MaterialsHand Gesture RecognitionCHI
ForcePinch: Force-Responsive Spatial Interaction for Tracking Speed Control in XRSpatial interaction in 3D environments requires balancing efficiency and precision, which requires dynamic tracking speed adjustments. However, existing techniques often couple tracking speed adjustments directly with hand movements, reducing interaction flexibility. Inspired by the natural friction control inherent in the physical world, we introduce ForcePinch, a novel force-responsive spatial interaction method that enables users to intuitively modulate pointer tracking speed and smoothly transition between rapid and precise movements by varying their pinching force. To implement this concept, we developed a hardware prototype integrating a pressure sensor with a customizable mapping function that translates pinching force into tracking speed adjustments. We conducted a user study with 20 participants performing well-established 1D, 2D, and 3D object manipulation tasks, comparing ForcePinch against the distance-responsive technique Go-Go and speed-responsive technique PRISM. Results highlight distinctive characteristics of the force-responsive approach across different interaction contexts. Drawing on these findings, we highlight the contextual meaning and versatility of force-responsive interactions through four illustrative examples, aiming to inform and inspire future spatial interaction design.2025CZChenyang Zhang et al.In-Vehicle Haptic, Audio & Multimodal FeedbackForce Feedback & Pseudo-Haptic WeightImmersion & Presence ResearchCHI