Skip to content
AI News HubLIVE
Original source2 min read

From Visual Widgets to UI Code: Efficient Tool-Grounded Generation

Summary

arXiv paper introduces WidgetGen, a lightweight tool-grounded framework that extracts observable text and color evidence, performs high-level layout and optional chart reasoning, and directly generates executable JSX, outperforming direct prompting and the structured Widget2Code pipeline on most visual reconstruction metrics across six multimodal models and 1,000 held-out widgets, while reconstruction-derived image-code pairs improve six Qwen-family open-weight models via supervised fine-tuning.

SourcearXiv Computer VisionAuthor: Houston H. Zhang, Tao Zhang, Li Gu, Linfeng Ye, Yuanhao Yu, Xinxin Zuo, Yang Wang, Zhixiang Chi
From Visual Widgets to UI Code: Efficient Tool-Grounded Generation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 12 Aug 2026]

Title:From Visual Widgets to UI Code: Efficient Tool-Grounded Generation

View a PDF of the paper titled From Visual Widgets to UI Code: Efficient Tool-Grounded Generation, by Houston H. Zhang and 7 other authors

View PDF HTML (experimental)

Abstract:Existing screenshot-to-code systems face a trade-off between flexibility and controllability. Direct multimodal generation can hallucinate visible details, whereas structured pipelines reduce such errors through component-wise decomposition, predefined templates, and customized intermediate representations. These structures, however, introduce additional generative orchestration and restrict outputs to designs covered by the representation. We investigate whether selective tool grounding can improve the fidelity--efficiency trade-off of direct widget-to-code generation. We introduce \textbf{WidgetGen}, a lightweight tool-grounded framework that extracts observable text and color evidence, performs high-level layout and optional chart reasoning, and directly generates executable JavaScript XML (\emph{JSX}). This design reduces reliance on component-wise generation while avoiding a fixed UI schema. Across six multimodal models and \(1{,}000\) held-out widgets, WidgetGen outperforms direct prompting and the structured Widget2Code pipeline on most visual reconstruction metrics, with consistent gains in area, legibility, and style. Finally, reconstruction-derived image-code pairs improve six Qwen-family open-weight models across every reported metric through supervised fine-tuning. These results establish WidgetGen as a strong lightweight baseline and show that selective evidence grounding offers an effective alternative to extensive representation constraints.

Comments: ECCV2026 (MUCG Workshop)

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Cite as: arXiv:2608.12611 [cs.CV]

(or arXiv:2608.12611v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2608.12611

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zhixiang Chi [view email] [v1] Wed, 12 Aug 2026 21:49:22 UTC (3,423 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled From Visual Widgets to UI Code: Efficient Tool-Grounded Generation, by Houston H. Zhang and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-08

Change to browse by:

cs cs.LG

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • WidgetGen replaces component-wise decomposition and fixed UI schemas with selective tool grounding to avoid hallucinated visual details.
  • Across six multimodal models and 1,000 held-out widgets, it consistently improves area, legibility, and style metrics over direct prompting and Widget2Code.
  • Reconstruction-derived image-code pairs boost six Qwen-family open-weight models on every reported metric through supervised fine-tuning.
  • The work was accepted at the ECCV2026 MUCG Workshop and spans computer vision and machine learning.

Highlights and analysis are generated automatically and may contain errors. Check the original source.