ui framework development

研究探讨了低成本小模型在基于A2UI的UI生成中能否达到高质量，通过调整监督微调数据构建方法、模型大小和组件目录大小来实现。

This study addresses the lack of empirical evidence on the real-world impact of UI testing frameworks in CI/CD pipelines. Using GitHub API data collection, YAML configuration parsing, CI log metric extraction, and controlled time-series analysis across open-source repositories, we systematically quantify the integration patterns and effects of Selenium, Playwright, and Cypress within GitHub Actions workflows. Results show that UI testing significantly improves test pass-rate stability but increases mean build duration by 12% initially. Highly active repositories prefer Playwright—its built-in retry mechanism reduces flaky-test-induced pipeline interruptions by 35%. This work fills a critical gap in understanding UI testing’s practical implications in production CI/CD environments, providing data-driven insights for quality assurance strategy design and framework selection.

This work addresses the inefficiency and lack of guidance faced by front-end developers when manually selecting plausible and natural attribute values for instantiating reusable UI components within a vast design space. To tackle this challenge, the paper introduces the concept of “discriminative variants,” which uniquely integrates symbolic reasoning with large language models (LLMs). Symbolic reasoning identifies visually salient attributes, while the LLM leverages real-world knowledge to generate component instances that balance fidelity to exemplars with meaningful differentiation. This approach shifts the paradigm from ad hoc manual configuration to structured exploration of the design space. A user study (n=12) demonstrates that the generated variants effectively aid developers in comprehending the design space, significantly improving both instantiation efficiency and user experience, while maintaining strong domain relevance.

Existing design-to-code approaches generate flat, unstructured code lacking componentization support, resulting in low cohesion, high coupling, and poor maintainability. To address this, we propose a vision-structure alignment paradigm for end-to-end generation of modular frontend code from UI screenshots. Our method comprises three key innovations: (1) a spatially aware Transformer that explicitly models geometric relationships among interface elements; (2) heuristic UI pattern matching to identify reusable, semantically meaningful component structures; and (3) a schema-driven LLM synthesis engine that generates type-safe, framework-compliant (React/Angular) componentized code. Evaluated on multiple benchmarks, our approach significantly improves code modularity and architectural consistency, surpassing state-of-the-art methods. It is the first to reliably map pixel-level UI inputs to production-grade, maintainable frontend engineering artifacts.

Existing UI prototyping tools provide weak support for integrating design artifacts such as screenshots and sketches, hindering component reuse, semantic integration, and cross-role collaboration. This paper proposes a novel UI prototyping paradigm grounded in Conceptual Blending Theory, the first to concretize cognitive-science-based blending mechanisms into an interactive tool. It enables semantic-level element mixing across heterogeneous design examples through example-driven component extraction and semantic alignment, lightweight vision–semantics mapping, and real-time blended preview—facilitating staged intent articulation by developers. An empirical study with 14 frontend developers demonstrates that the approach significantly reduces prototype initiation time (average improvement of 42%), stimulates highly unexpected creative combinations (68% novel composition rate), and enhances design–development collaboration efficiency.

This work addresses the lack of transparency and controllability in existing generative UI design tools, which often force users into trial-and-error prompting without insight into the model’s reasoning. To overcome this, the authors propose LegoUI, a novel framework that introduces, for the first time, a staged and traceable UI-specific domain-specific language (UI-DSL). This approach decomposes the generation process into interpretable steps and records provenance information at each stage, enabling user intervention and iterative refinement. While maintaining high generation efficiency, LegoUI significantly enhances the transparency and controllability of the design workflow. Evaluated on 40 real-world tasks, the method achieves over 95% accuracy in requirement analysis, producing complete and non-redundant outputs. User studies further demonstrate its substantial advantages over current tools in intent alignment, transparency, and user control.

为了解决生成式用户界面难以直接控制设计意图的问题，GUIDE系统通过设计师的持续互动和修改来优化界面生成，并采用自适应一致性评分模型确保符合设计要求。

Existing design-to-code generation methods are difficult to compare fairly due to the absence of a unified evaluation protocol, hindering both research progress and practical adoption. This work addresses this gap by introducing the first standardized evaluation framework tailored to this task, accompanied by an open-source, modular toolkit that unifies environment setup, model inference, code rendering, and multi-dimensional metric computation in a plug-and-play manner. The platform not only standardizes the evaluation pipeline and enables visual analysis but also conducts systematic benchmarking of state-of-the-art approaches, revealing critical directions for improvement. By providing a reproducible and extensible infrastructure, this study establishes a foundational resource for the community to advance the field in a consistent and measurable way.

Existing screenshot-to-code approaches struggle to balance flexibility and controllability: end-to-end generation often suffers from hallucination, while structured pipelines constrain design expressiveness. This work proposes WidgetGen, a lightweight, tool-anchored framework that selectively invokes modular components—such as text/color extraction, layout reasoning, and chart recognition—to directly synthesize executable JSX code. By avoiding rigid UI templates and reducing reliance on component-level generation, WidgetGen achieves greater adaptability. Experimental results demonstrate that WidgetGen significantly outperforms both direct prompting and the Widget2Code pipeline across 1,000 held-out UI controls, yielding consistent improvements in region accuracy, code readability, and style fidelity. Furthermore, supervised fine-tuning with WidgetGen effectively enhances the code generation capabilities of Qwen-family models.

This work addresses the labor-intensive nature of presentation tasks—such as formatting and layout—in dashboard authoring, which currently lack support for partial reuse. Through a systematic user study, we characterize the needs and challenges associated with cross-source reuse of visual presentation elements. Building on these insights, we propose a novel paradigm that enables partial reuse of styles and layouts from multiple existing dashboards. We design and implement ReDash, a prototype system embodying this approach, and demonstrate through proof-of-concept experiments that our mechanism effectively overcomes key barriers in common reuse scenarios. The results show a significant improvement in authoring efficiency, confirming the feasibility and practical potential of partial reuse in real-world dashboard creation.