accessible interaction design

This study addresses the limitations of current generative AI systems, which rely heavily on chat-based interactions and impose high cognitive demands that exclude individuals with intellectual disabilities—particularly in prompt formulation, information processing, and credibility assessment. To bridge this gap, the authors propose a dual-layer interaction framework integrating structural scaffolds (e.g., reliability indicators, context management) and experiential scaffolds (e.g., pacing control, multimodal guidance). Developed through a collaborative design approach combining computer science and industrial design, this framework expands the design space for cognitively inclusive AI. The work identifies core mechanisms—including initial calibration, proactive prompting, and direct manipulation of response segments—to formulate an interaction paradigm tailored to cognitively diverse users, thereby laying the groundwork for expert refinement and empirical validation.

Current assistive and augmentative communication (AAC) system design suffers from insufficient user involvement and low process accessibility, particularly for individuals with communication disabilities. Method: This study proposes a two-stage participatory design methodology specifically tailored for AAC users. It integrates closed-loop user feedback, accessibility-specific evaluation, and iterative human–computer interaction (HCI) design techniques—focusing on optimizing task structure, interaction modalities, and collaborative mechanisms to align with users’ cognitive, perceptual, and motor capabilities. Contribution/Results: The work introduces the first AAC-dedicated participatory framework that balances structural rigor with methodological flexibility. Empirical validation confirms its feasibility and demonstrates significant improvements in depth of user engagement, expressive efficacy, and influence of user input on design decisions. This approach advances inclusive HCI by delivering a reusable methodological foundation and actionable implementation pathway for equitable, user-centered AAC development.

In HCI, accessible design faces challenges of resource intensity, difficulty in balancing individual user needs with scalable adaptation, and limited support for inclusive interface customization. Method: This paper proposes a human–computer collaborative optimization framework wherein designers shift from manual implementation to constraint curation, while the system jointly optimizes text size, color contrast, layout, and interaction modalities—guided by predefined accessibility constraints, multimodal real-time feedback, and personalized prompts. Contribution/Results: We introduce the first explainable human-in-the-loop (HITL) optimization paradigm tailored for inclusive design, integrating constraint-driven design space modeling, multimodal feedback aggregation, and joint optimization of accessibility parameters. The approach enables user-centered, traceable, and efficient iterative interface adaptation. Experiments demonstrate significant reductions in prototyping validation costs, robust support for personalized interface generation across diverse disability scenarios, and a dynamic equilibrium between automation efficiency and expert design judgment.

Current HCI prototyping tools and methods present significant accessibility barriers, impeding substantive participation of disabled researchers and practitioners in technology design. To address this, we adopt a participatory design approach grounded in universal design principles, conducting iterative workshops, hands-on prototyping sessions, and collaborative ideation activities to systematically identify limitations of existing tools, refactor open-source resources, and develop novel accessible prototyping tools and methodologies. Key contributions include: (1) the first low-threshold prototyping workflow explicitly designed for disabled creators; (2) a paradigm shift framing “accessibility as design capacity”; and (3) a consensus framework and open-source toolkit co-developed at the CHI 2025 full-day workshop. Collectively, these advances catalyze a field-wide transition—from designing *for* disabled people to designing *with* them—establishing foundational methodological scaffolding and actionable pathways toward inclusive technology ecosystems.

This study addresses the limitations of traditional handcrafted user personas, which are often abstract, costly to produce, and difficult to translate into actionable design features, thereby hindering their practical utility in product design. To overcome these challenges, this work proposes the first interactive system grounded in multimodal large language models (MLLMs) that integrates demographic data with an interactive interface to enable designers to generate fine-grained user personas. The system further automatically derives and restructures these personas into structured design features, achieving an end-to-end transformation from abstract representations to concrete design elements. In an evaluation with twelve professional designers, the approach significantly outperformed a chat-based baseline in terms of persona engagement, perceived transparency, and user satisfaction.

This study addresses the limited generalizability and scalability of existing assistive human–robot collaboration systems, which often rely on highly individualized designs and face high implementation barriers for universal design principles. To overcome these challenges, this work proposes an adaptive collaboration framework that integrates user personas derived from representative disability categories with universal design principles. By applying design thinking to decompose task actions and employing behavior trees to dynamically modulate the robot’s level of assistance, the framework enables online adaptation to diverse disability needs. This approach represents the first systematic integration of user personas and universal design in assistive robotics. Evaluated on a cardboard-folding task, the method demonstrated effectiveness across seven disability personas, generating adaptive strategies that are both comprehensive and aligned with universal design principles.

Current retail AI frontends commonly operate under an “ideal user” assumption, overlooking the perceptual, motor, and cognitive differences of users with disabilities and diverse needs, thereby creating systemic accessibility gaps. This study employs qualitative analysis of representative applications—including virtual assistants, virtual try-on systems, and hyper-personalized recommendation engines—to uncover interaction design mechanisms that inadvertently exclude atypical users. It identifies the root cause not in technical limitations but in procurement and organizational processes that lack accessibility mandates. To address this, the work proposes a “front-end assurance” framework that aligns the multimodal capabilities and intelligence claims of AI systems with the genuine diversity of end users, filling a critical gap in existing AI governance regarding user experience and advancing the practical implementation of inclusive design in commercial contexts.

This work addresses the limitations of traditional static accessibility standards in handling dynamic challenges posed by user-generated content—such as blurry images, missing descriptions, and disorganized layouts—which often hinder accessibility for people with visual impairments, low vision, or age-related needs. To bridge this gap, the authors propose a “generative user interface” approach that dynamically restructures interfaces at runtime to accommodate diverse user requirements. The method employs three key interventions: real-time HTML regeneration, conversational guidance, and audio-assisted photography. By shifting the designer’s role from layout implementation to strategy formulation, this approach effectively mitigates coverage gaps in existing accessibility standards. Evaluated on a consumer-to-consumer (C2C) e-commerce platform, the framework significantly enhances accessibility for heterogeneous user groups and expands the application frontier of generative UI within human-computer interaction.

This work addresses the lack of explicit modeling of abstraction mechanisms in existing interactive system design, which hinders actionable design guidance. Through a systematic review of 457 publications, the study proposes the first abstraction-centered design space for interactive systems, structured around six core dimensions. Leveraging this framework, it reconceptualizes the Gulf of Execution and Evaluation model to reveal the cognitive and design mechanisms by which users and systems bridge the abstraction gap. By explicitly integrating abstraction into the theoretical foundations of human–computer interaction, this research synthesizes prior work, establishes a coherent theoretical basis, and offers systematic practical guidance for designing and evaluating abstraction mechanisms in interactive systems, thereby charting new directions for future inquiry.

This study addresses the transparency challenges in large language model–driven conversational recommender systems, which, despite their fluency, often undermine users’ understanding, trust, and control over recommendations. The authors design and implement a laptop recommendation chatbot featuring constraint-based generation, on-demand ranking explanations, and product comparison capabilities. Through a moderated think-aloud usability study, they empirically find that “design transparency” does not necessarily enhance user comprehension and identify ranking explanations as the most severe usability issue. The study further codes and prioritizes identified problems by severity, revealing that while users appreciate the system’s reduction of cognitive load, they strongly desire more direct manipulation controls. These findings offer critical design implications for human-centered conversational recommender systems.