user experience

Designers often struggle to effectively apply insights from human-computer interaction (HCI) research due to challenges in retrieval, disciplinary terminology barriers, and a lack of contextualized, actionable guidance. To address this gap, this work proposes ReFinE—the first Figma plugin that automatically synthesizes HCI research findings and integrates them directly into the UI design workflow. Leveraging natural language processing and context-aware recommendation techniques, ReFinE delivers real-time, visual, and actionable design suggestions tailored to the designer’s current task. Findings from a user study demonstrate that ReFinE significantly reduces cognitive load, enhances designers’ ability to incorporate empirical research evidence into their practice, improves design quality, and accelerates iterative prototyping cycles.

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.

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.

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.

Designers lack a bidirectional mechanism to translate design requirements into large language model (LLM) behaviors—and vice versa—hindering human-centered LLM integration in UX practice. Method: We propose the “Designer-Centric Adaptation” paradigm, emphasizing dynamic, human-in-the-loop shaping and responsive refinement of LLM behavior. Based on this, we developed Canvil—a Figma plugin enabling real-time parameter tuning, feedback-driven closed loops, and collaborative iterative design. Contribution/Results: Through design probes, co-design workshops with six designer pairs, and qualitative thematic coding, we demonstrate that designers effectively optimize both LLM adaptation strategies and interface designs using Canvil. We synthesize a cross-role collaboration workflow and establish the first systematic methodology for human-centered LLM adaptation—bridging the longstanding gap between UX design and LLM engineering, and advancing practice-oriented, human-centered LLM application development.

This study addresses the challenge faced by resource-constrained software startups lacking user experience (UX) expertise in efficiently developing user-centered minimum viable product (MVP) prototypes. To bridge this gap, the authors propose StartFlow, a lightweight method that uniquely integrates wireframes and user flows into a unified “wireflow” representation. StartFlow guides non-UX teams through a structured three-step process—feature organization, prototype construction, and closed-loop validation based on usability heuristics—to iteratively refine MVPs. Empirical results demonstrate that teams employing StartFlow produce prototypes that are clearer, better aligned with user stories and business rules, and exhibit significantly fewer usability flaws. Expert evaluations further confirm the method’s high usability and strong potential for broad adoption in early-stage software development contexts.

This work addresses the creative stagnation often induced by existing generative design tools that directly output complete images. To overcome this limitation, the authors propose a multi-stage, compositional AI-assisted design approach that emulates professional designers’ workflows: it first structurally interprets ambiguous design requests, then generates candidate elements—such as objects, backgrounds, typography, layout, and composition—separately, and finally enables interactive recombination. This method formalizes real-world design processes into a computable system for the first time, decoupling requirement interpretation, element generation, and composition to substantially enhance prompt diversity and alignment with user intent. User studies demonstrate that the system outperforms baseline approaches in both requirement comprehension accuracy and designer-rated quality, revealing a productive trade-off between structured workflow, creative clarity, and efficiency despite slightly longer generation times.

Existing vision-language models (VLMs) lack systematic evaluation benchmarks for tool-driven UI design tasks—such as those performed in Figma or Sketch—hindering progress in professional design automation. Method: We introduce CANVAS, the first benchmark tailored for tool-augmented VLMs in UI design, comprising 598 context-aware design tasks across 30 mobile UI scenarios. It explicitly distinguishes “design reproduction” and “design modification” tasks, built upon real-world UI data with human-annotated ground truth. Our methodology employs a context-aware VLM–tool API co-execution framework for precise tool invocation. Contribution/Results: Experiments demonstrate that state-of-the-art VLMs exhibit nascent capability in collaborative tool-based design; however, strategic tool selection and design quality remain critical bottlenecks. CANVAS provides a reproducible, empirically grounded evaluation framework to advance VLM interaction, iterative refinement, and integration within professional design software.

This study addresses the frequent disconnect between design metaphors employed by platforms and users’ actual experiences, as well as the lack of systematic evaluation methods in this domain. It proposes a novel comparative framework that juxtaposes designer-intended metaphors with user-generated ones, integrating mixed-method approaches—including metaphor extraction, historical web content analysis, and user surveys—to examine 21 official design metaphors and 554 user metaphors across three major platforms (ChatGPT, Twitter, and YouTube) since their launch. A user rating mechanism is introduced to quantitatively measure resonance levels. Findings reveal that design metaphors often misalign with user cognition, and even when form matches, they do not necessarily elicit broad resonance—offering a new pathway for evaluating user experience and optimizing metaphor-driven design.

In early conceptual design, motion behavior validation is inefficient, hand-drawn sketches inadequately capture dynamic characteristics, and conversion to CAD/CAE models is time-consuming. To address these challenges, this paper proposes a rapid modeling and real-time simulation method for mechanism motion based on interactive sketching. The method integrates lightweight sketch recognition, automatic topological parsing, and 2D kinematic solving, enabling natural digitalization of mechanism structures and millisecond-level motion feedback within a 2D sketching environment. Its key innovation lies in embedding motion constraints directly into the sketching process, supporting immediate dynamic validation and iterative refinement of design intent. User studies demonstrate a 77% reduction in cognitive load compared to conventional workflows, along with significant improvements in design communication efficiency and user satisfaction—thereby validating the method’s effectiveness and usability in early-stage conceptual design.