"Same Voice, Different Language": An Exploration of Voice-Cloned Translation to Support Non-Native Speakers in Online MeetingsCross-lingual meetings have become essential for global collaboration, yet current translation technologies often strip away vocal identity — the unique speaker characteristics that convey nuance and social presence. While generic text-to-speech (TTS) provides basic intelligibility, it creates a disconnect between speakers and their translated voices, potentially undermining engagement and comprehension. This paper investigates whether voice cloning technology can bridge this gap by preserving speaker identity in real-time translation. We present a controlled study comparing four voice conditions in meeting interpretation: original speech, gender-neutral TTS, gender-matched TTS, and voice cloning. Through a within-subjects experiment with 45 participants, we demonstrate that voice cloning significantly reduces mental workload ($p < .001$) and enhances user experience across pragmatic quality ($p < .001$), hedonic quality ($p < .001$), and overall satisfaction ($p < .001$) compared to traditional TTS. While original speech maintained advantages in naturalness, voice cloning achieved superior intelligibility, social impression, and user preference. Qualitative analysis revealed that participants valued voice cloning for preserving speaker identity and improving conversation tracking in multi-speaker scenarios. Our findings suggest that identity-preserving translation represents a significant advancement for cross-lingual communication systems, offering both cognitive and social benefits. We conclude with design implications for integrating voice cloning into meeting platforms while addressing ethical considerations around consent and transparency.2026YMYong Ma et al.University of BergenMultilingual & Cross-Cultural Voice InteractionVoice User Interface (VUI) DesignHuman-LLM CollaborationIUI
SIA: A Framework for Context-Aware Intent Clarification in Speech-Driven Immersive AnalyticsThe rise of generative AI has increased attention to voice interfaces. In immersive analytics, we conceptualize this trend as Speech-driven Immersive Analytics. While speech interfaces enable natural interactions, users, especially novices, still face a learning curve in articulating analytic intent and exploring data during the foraging phase. Prior work has primarily addressed these challenges through multimodal interaction or textual disambiguation. We introduce a context-aware Speech-driven Immersive Analytics framework (SIA) as a speech-oriented approach that leverages speech acts to convey actionable intent. This framework (SIA) was designed based on a formative study, a prototype development, three technical studies, and a user study. By extracting speech acts from utterances, SIA infers analytic tasks and embodiment tendencies, then integrates them with spatial, chart, and data context to generate feedforward: previews of potential actions and outcomes. The formative study identified user needs. The technical studies demonstrated that SIA improved the inference quality, enabling context-aware feedforward generation. The user study highlighted that the SIA-based prototype was responsive and intuitive, and feedforward helped users learn during the onboarding phase of data exploration. In particular, the user study identified which feedforward elements participants referenced and how they applied them when expressing intent in immersive analytics. Our key technical findings emphasize that the ensemble model, embedded in the Uncertainty Estimator, improves accuracy and stabilizes task inference. The Projector's context summary was critical in generating context-aware feedforward. Based on these results, we discuss future research directions for intelligent Speech-driven Immersive Analytics.2026HSHyemi Song et al.University of MarylandVoice User Interface (VUI) DesignSocial & Collaborative VRInteractive Data VisualizationIUI
ROOTED in Us: A Framework for Cultivating Community Ecosystems through Relationships and DataAs data becomes integral to civic processes and resource distribution, there is a need for methods in which communities generate, interpret, and act on data to address their priorities. We introduce ROOTED (Reclaiming and Organizing Our Truths for Equity through Data), a community-centered framework grounded in Black Feminist Thought. By cultivating community data practices, ROOTED helps residents leverage their local insights, lived experiences, and data to pursue equitable outcomes by using data as a tool for advocacy, organizing, and local transformation. Through two case studies, we demonstrate how researchers and communities can collaboratively implement ROOTED. Our findings suggest that residents use data to build power and relationships to collectively achieve their goals. This paper contributes a framework and case study examples that demonstrate how to design community data systems and practices that produce actionable outcomes aligned with residents’ visions for their futures.2026SESheena Erete et al.University of Maryland College ParkEmpowerment of Marginalized GroupsCitizen Science & Crowdsourced DataCommunity Engagement & Civic TechnologyCHI
As Content and Layout Co-Evolve: TangibleSite for Scaffolding Blind People’s Webpage Design through Multimodal InteractionCreating webpages requires generating content and arranging layout while iteratively refining both to achieve a coherent design, a process that can be challenging for blind individuals. To understand how blind designers navigate this process, we conducted two rounds of co-design sessions with blind participants, using design probes to elicit their strategies and support needs. Our findings reveal a preference for content and layout to co-evolve, but this process requires external support through cues that situate local elements within the broader page structure as well as multimodal interactions. Building on these insights, we developed TangibleSite, an accessible web design tool that provides real-time multimodal feedback through tangible, auditory, and speech-based interactions. TangibleSite enables blind individuals to create, edit, and reposition webpage elements while integrating content and layout decisions. A formative evaluation with six blind participants demonstrated that TangibleSite enabled independent webpage creation, supported refinement across content and layout, and reduced barriers to achieving visually consistent designs.2026JLJiasheng Li et al.University of MarylandVisual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)Universal & Inclusive DesignTangible User Interface DesignCHI
Interrogating the “Us” Versus “Them” Dichotomy in Technology Research with Older Adults Research on technology for older people focuses on older people’s experiences–and understandably so. However, the phenomena of othering, or seeing this group as different and worse off, is a persistent problem. In this project, we turned inwards through an 8-month collaborative autoethnography to understand our own experiences with technology issues and supporting others in technology use. We found that each member of our mixed age group faced pervasive and burdensome technology issues and recognized that some of the burden is associated with the evolution of technology tools. Our work contributes an expanded understanding of aging as a sociotechnical process and identifies counternarratives to implicit assumptions we held as HCI researchers working with older people. Our research also shows how reflexive positional methods can surface often unexamined experiences with technology issues and aging among researchers.2026ALAmanda Lazar et al.University of MarylandAging-Friendly Technology DesignTechnology Ethics & Critical HCIUser Research Methods (Interviews, Surveys, Observation)CHI
From A to Zines: Narrative Threat Modeling in U.S. Reproductive Health MediaPost-Roe, people capable of pregnancy face fragmented reproductive privacy landscapes in the United States (U.S.), with risks spanning legal, digital, and interpersonal domains. These conditions demand new forms of privacy guidance. We analyzed 212 reproductive health zines—a DIY, subversive, and collectively produced media genre—to understand how they communicate reproductive health information. Zines foreground embodied, first-person narratives interwoven with historical context, medical guidance, and activist messaging. We argue their use of subversive or alternative medical knowledge enhanced credibility in contexts of low institutional trust. While some zines offer digital privacy strategies, many focus on avoiding institutional exposure altogether. These emotionally resonant, context-sensitive accounts illustrate threat models attuned to entangled risks of interpersonal betrayal, legal precarity, and surveillance. We conclude with design implications for how zines might better support people navigating reproductive risk through what we call narrative threat modeling—a situated practice that communicates privacy strategies through story, tone, and form rather than technical instructions or prescriptive checklists.2026CSCora Sula et al.George Mason UniversityPrivacy by Design & User ControlPrivacy Perception & Decision-MakingEmpowerment of Marginalized GroupsCHI
I, Robot? Exploring Ultra-Personalized AI-Powered AAC; an Autoethnographic AccountGeneric AI auto-complete for message composition often fails to capture the nuance of personal identity, requiring editing. While harmless in low-stakes settings, for users of Augmentative and Alternative Communication (AAC) devices, who rely on such systems to communicate, this burden is severe. Intuitively, the need for edits would be lower if language models were personalized to the specific user's communication. While personalization is technically feasible, it raises questions about how such systems affect AAC users’ agency, identity, and privacy. We conducted an autoethnographic study in three phases: (1) seven months of collecting all the lead author’s AAC communication data, (2) fine-tuning a model on this dataset, and (3) three months of daily use of personalized AI suggestions. We observed that: logging everyday conversations reshaped the author’s sense of agency, model training selectively amplified or muted aspects of his identity, and suggestions occasionally resurfaced private details outside their original context. We find that ultra-personalized AAC reshapes communication by continually renegotiating agency, identity, and privacy between user and model. We highlight design directions for building personalized AAC technology that supports expressive, authentic communication.2026TWTobias M Weinberg et al.Cornell TechAugmentative & Alternative Communication (AAC)Privacy & Data Ownership in Self-TrackingGenerative AI (Text, Image, Music, Video)CHI
Hybrid LLM-Embedded Dialogue Agents for Learner Reflection: Designing Responsive and Theory-Driven InteractionsDialogue systems have long supported learner reflections, with theoretically grounded, rule-based designs offering structured scaffolding but often struggling to respond to shifts in engagement. Large Language Models (LLMs), in contrast, can generate context-sensitive responses but are not informed by decades of research on how learning interactions should be structured, raising questions about their alignment with pedagogical theories. This paper presents a hybrid dialogue system that embeds LLM responsiveness within a theory-aligned, rule-based framework to support learner reflections in a culturally responsive robotics summer camp. The rule-based structure grounds dialogue in self-regulated learning theory, while the LLM decides when and how to prompt deeper reflections, responding to evolving conversation context. We analyze themes across dialogues to explore how our hybrid system shaped learner reflections. Our findings indicate that LLM-embedded dialogues supported richer learner reflections on goals and activities, but also introduced challenges due to repetitiveness and misalignment in prompts, reducing engagement.2026PSParas Sharma et al.University of PittsburghHuman-LLM CollaborationIntelligent Tutoring Systems & Learning AnalyticsCollaborative Learning & Peer TeachingCHI
Designing Multi-Robot Ground Video Sensemaking with Public Safety ProfessionalsVideos from fleets of ground robots can advance public safety by providing scalable situational awareness and reducing professionals’ burden. Yet little is known about how to design and integrate multi-robot videos into public safety workflows. Collaborating with six police agencies, we examined how such videos could be made practical. In Study 1, we presented the first testbed for multi-robot ground video sensemaking. The testbed includes 38 events-of-interest (EoI) relevant to public safety, a dataset of 20 robot patrol videos (10 day/night pairs) covering EoI types, and 6 design requirements aimed at improving current video sensemaking practices. In Study 2, we built MRVS, a tool that augments multi-robot patrol video streams with a prompt-engineered video understanding model. Participants reported reduced manual workload and greater confidence with LLM-based explanations, while noting concerns about false alarms and privacy. We conclude with implications for designing future multi-robot video sensemaking tools.2026PZPuqi Zhou et al.George Mason UniversityTeleoperation & TelepresenceExplainable AI (XAI)AI-Assisted Decision-Making & AutomationCHI
"Even though you feel like it's good, it isn't": Surfacing the Ethical Priorities of Powerful Male Youth Targeted for Racial Oppression through Evaluating and Co-Designing XR Utopian and Dystopian Use CasesExtended reality (XR) technologies have become more advanced and affordable in recent years, leading to greater familiarity and adoption among US families and youth-serving institutions. While these tools show promise in enhancing children’s education, healthcare, and recreation, ethical considerations around safety, accessibility, and impact—particularly for children from historically marginalized racial and ethnic groups—warrant further investigation. This study engaged 17 local, primarily Black, middle school male youth in evaluating and co-designing utopian and dystopian XR use cases to surface their ethical perspectives. We found that our participants emphasized individual responsibilities like self-discipline, self-care, and skepticism of virtual content; broader societal concerns about entrapment and diminished community agency; and design opportunities for promoting equity and access. Based on these findings, we offer design and methodological recommendations to better integrate the perspectives of male youth targeted for racial oppression into XR innovation to ensure that these tools are ethical, inclusive, and responsive to the communities they serve.2026EBElana B Blinder et al.University of MarylandSocial & Collaborative VRInclusive DesignGender & Race Issues in HCICHI
“We Figure It Out Together”: A Framework for Relational Communication in Disabled and Neurodivergent LGBTQIA+ Romantic PartnershipsDisabled and neurodivergent LGBTQIA+ individuals often co-create adaptive communication practices within their romantic partnerships; however, little is known about how these strategies evolve over time. We present findings from a diary and co-design study with five disabled LGBTQIA+ partnerships, documenting how communication is negotiated and sustained through shifting relational, emotional, and access needs. We argue that this ongoing work constitutes a relational infrastructure—the communicative system of shared practices, adaptive routines, and negotiated meanings that disabled and neurodivergent LGBTQIA+ partners co-create to navigate their shared lives. To model these dynamics, we introduce the Relational Access Framework for Communication (RAF-Comm): A Model for Disabled and Neurodivergent LGBTQIA+ Partnerships, a provisional and generative framework that centers identity, co-creation, and adaptation as fundamental to relational accessibility. Our findings highlight the conditional use of technology and the importance of non-use as a valid, relationship-preserving choice. We conclude with design implications for technologies that support the personal, continuously evolving ecosystems of care these partnerships create for themselves.2026KCKirk Andrew Crawford et al.University of Maryland, Baltimore CountyEmpowerment of Marginalized GroupsInclusive DesignCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)CHI
Are Conversational AI Agents the Way Out? Co-Designing Reader-Oriented News Experiences with Immigrants and JournalistsRecent discussions at the intersection of journalism, HCI, and human-centered computing ask how technologies can help create reader-oriented news experiences. The current paper takes up this initiative by focusing on immigrant readers, a group who reports significant difficulties engaging with mainstream news yet has received limited attention in prior research. We report findings from our co-design research with eleven immigrant readers living in the United States and seven journalists working in the same region, aiming to enhance the news experience of the former. Data collected from all participants revealed an “unaddressed-or-unaccountable” paradox that challenges value alignment across immigrant readers and journalists. This paradox points to four metaphors regarding how conversational AI agents can be designed to assist news reading. Each metaphor requires conversational AI, journalists, and immigrant readers to coordinate their shared responsibilities in a distinct manner. These findings provide insights into reader-oriented news experiences with AI in the loop.2026YZYongle Zhang et al.University of MarylandConversational ChatbotsAI Ethics, Fairness & AccountabilityCommunity Collaboration & WikipediaCHI
Through a Live Elections Dashboard, Darkly: Managing Expectations and Trust in Progressive Vote Counting During the 2024 U.S. ElectionDuring U.S. elections, news outlets publish live dashboards to contextualize vote counting and manage public expectations. This proved challenging in 2020 amid election fraud allegations, sparking conversations about how data journalists might better visualize and explain live vote counting. To address this, we designed a dashboard to foster understanding of the progressive nature of vote counts and more realistic expectations of the vote counting timeline. We deployed it during the 2024 U.S. presidential election, showing it to 308 people with real results, and collected surveys and interviews on impressions and trust. We contribute: (1) a design process and framework for how audiences might form expectations around live data, (2) survey findings suggesting live forecasts slightly increased confidence in vote counting and slightly reduced belief in evidence of fraud, and (3) interview findings underscoring the importance of agency in viewing live data and tensions in the perceived usefulness of live forecasts. Our supplementary materials are available at https://osf.io/qxk2t/.2026MCMandi Cai et al.Northwestern UniversityInteractive Data VisualizationData StorytellingPrivacy Perception & Decision-MakingCHI
Codesigning Ripplet: an LLM-Assisted Assessment Authoring System Grounded in a Conceptual Model of Teachers’ WorkflowsAssessments are critical in education, but creating them can be difficult. To address this challenge in a grounded way, we partnered with 13 teachers in a seven-month codesign process. We developed a conceptual model that characterizes the iterative dual process where teachers develop assessments while simultaneously refining requirements. To enact this model in practice, we built Ripplet,\footnote{A demo video of the system is provided in supplemental materials.} a web-based tool with multilevel reusable interactions to support assessment authoring. The extended codesign revealed that Ripplet enabled teachers to create formative assessments they would not have otherwise made, shifted their practices from generation to curation, and helped them reflect more on assessment quality. In a user study with 15 additional teachers, compared to their current practices, teachers felt the results were more worth their effort and that assessment quality improved.2026YCYuan Cui et al.Northwestern UniversityHuman-LLM CollaborationParticipatory DesignPrototyping & User TestingCHI
Towards AI as Colleagues: Multi-Agent System Improves Structured Ideation ProcessesMost AI systems today are designed to manage tasks and execute predefined steps. This makes them effective for process coordination but limited in their ability to engage in joint problem-solving with humans or contribute new ideas. We introduce MultiColleagues, a multi-agent conversational system that shows how AI agents can act as colleagues by conversing with each other, sharing new ideas, and actively involving users in collaborative ideation processes. In a within-subjects study with 20 participants, we compared MultiColleagues to a single-agent baseline. Results show that MultiColleagues fostered stronger perceived social presence, and participants rated their outcomes as higher in quality and novelty, with more elaboration during ideation. These findings demonstrate the potential of AI agents to move beyond process partners toward colleagues that share intent, strengthen group dynamics, and collaborate with humans to advance ideas.2026KQKexin Quan et al.University of Illinois, Urbana-ChampaignHuman-LLM CollaborationCreative Collaboration & Feedback SystemsAI-Assisted Decision-Making & AutomationCHI
Say It My Way: Exploring Control in Conversational Visual Question Answering with Blind UsersPrompting and steering techniques are well-established in general-purpose generative-AI, yet assistive visual-question-answering (VQA) tools for blind users still follow rigid interaction-patterns with limited opportunities for customization. User-control can be helpful when system responses are misaligned with their goals and contexts, a gap that becomes especially consequential for blind users that may rely on these systems for access. We invite 11 blind users to customize their interactions with a real-world conversational-VQA system. Drawing on 418 interactions, reflections, and post-study interviews, we analyze prompting-based techniques participants adopted, including those introduced in the study and those developed independently in real-world settings. VQA interactions were often lengthy: participants averaged 3 turns, sometimes up to 21, with input-text typically tenfold shorter than the responses they heard. Built on state-of-the-art LLMs, the system lacked verbosity controls, was limited in estimating distance in space and time, relied on inaccessible image-framing, and offered little-to-no camera-guidance. We discuss how customization techniques such as prompt engineering can help participants work around these limitations. Alongside a new publicly available dataset, we offer insights for interaction design at both query and system levels.2026FZFarnaz Zamiri Zeraati et al.University of MarylandVoice AccessibilityGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationCHI
When Stereotypes GTG: The Impact of Predictive Text Suggestions on Gender Bias in Human-AI Co-WritingAI-based systems such as language models have been shown to replicate and even amplify social biases reflected in their training data. Among other questionable behaviors, this can lead to AI-generated text--and text suggestions--that contain normatively inappropriate stereotypical associations. Little is known, however, about how this behavior impacts the writing produced by people using these systems. We address this gap by measuring how much impact stereotypes or anti-stereotypes in English single-word LM predictive text suggestions have on the stories that people write using those tools in a co-writing scenario. We find that (n=414), LM suggestions that challenge stereotypes sometimes lead to a significantly increased rate of anti-stereotypical co-written stories. However, despite this increased rate of anti-stereotypical stories, pro-stereotypical narratives still dominated the co-written stories, demonstrating that technical debiasing is only a partially effective strategy to alleviate harms from human-AI collaboration.2026CBConnor Baumler et al.University of MarylandHuman-LLM CollaborationAI Ethics, Fairness & AccountabilityAlgorithmic Fairness & BiasCHI
Looking Beyond the Screen to Study the Technology Use of Older People Experiencing Cognitive ConcernsResearch with older adults has hinted at the ways that elements beyond the interface play a role in technology use, including videoconferencing. To further understand the range of materials and resources involved, we studied videoconferencing use by ten older individuals with cognitive concerns in a week-long study of interviews, observations, and a modified diary study. Our analysis identified that objects extending beyond software and hardware play a role in videoconferencing, including paper-based objects, personal items, and objects in the built environment. These objects support participants by externalizing information difficult to recall, distributing cognitive effort across time, and lowering cognitive load through their spatial placement and affordances. These insights point to opportunities for researchers working with older people to focus on the work happening outside of today's interfaces. We also discuss how the lens of distributed cognition could help us design better technologies to support age-related cognitive impairment.2026RHRuipu Hu et al.University of MarylandElderly Care & Dementia SupportAging-Friendly Technology DesignPrototyping & User TestingCHI
Understanding the Sociocultural Role of Makerspace Infrastructure When Developing Community-based Technology-rich Learning ProgramsUnderstanding how to design and implement equity-based approaches to technology-rich learning in community settings can lead to increased and diversified participation in computing. However, research has shown that making practices can be inequitable, particularly for populations who are situated in low-resourced settings. In US cities, recreation centers have been shown to be promising sites for equity-based hands-on maker learning. However, it is unclear what approaches are needed to create the necessary technical and social infrastructure at these sites to support community uptake. Our study investigates the infrastructure development process for an equity-based makerspace program as developed within city-run community recreation centers in two US cities over 3 years. We developed an infrastructure map depicting the ecosystem of multiple organizations that are involved in creating the program and identified how digital technologies within makerspaces function as sociocultural factors within this ecosystem.2026EHErin Higgins et al.Carnegie Mellon UniversityMakerspace CultureSustainable HCICommunity Engagement & Civic TechnologyCHI
FIXical I/O: Exploring the Effects of Real-time Error Sensing and Physical Intervention on Finger-based Motor Sequence LearningDexterous finger movements are critical for both everyday and specialized tasks. However, acquiring such skills is challenging, as it requires accurate sequence memory and fine finger coordination. Existing haptic training systems typically employ demonstration feedback, which physically guides correct movements, or post-error correction that intervenes after errors occur. While effective, these approaches can reduce learners’ autonomy or expose novices to repeated errors, which can harm motivation. We introduce FIXical I/O, a magnetic hand exoskeleton that enables three error feedback strategies by combining real-time motion sensing with electromagnet-based actuation: Preemptive Error Correction (nudging fingers away from incorrect actions), Preemptive Error Blocking (constraining erroneous movements before execution), and Post-Error Correction. We conducted a user study comparing these strategies in terms of learning performance and subjective experiences, such as perceived performance and sense of agency, thereby demonstrating the benefits of Preemptive Error Correction and providing design implications.2026KLKyungyeon Lee et al.University of MarylandForce Feedback & Pseudo-Haptic WeightHaptic WearablesVibrotactile Feedback & Skin StimulationCHI