# UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

> UniCoder trains a visual-to-code model for charts, SVGs and webpages. Its reinforcement-learning objective combines rendering checks, image similarity and code-derived visual attributes; low-reward training groups receive reference-code trajectories to improve exploration.

- Authors: Yaozhi Zheng; Yilei Jiang; Manyuan Zhang; Yuxuan Wan; Kaituo Feng; Tianshuo Peng; Bo Zhang; Xiangyu Yue
- Venue: arXiv
- Status: Preprint
- Publication / posting date: June 30, 2026
- Date source: arXiv v1 submission date; no separate proceedings or journal publication was verified.
- First arXiv submission: June 30, 2026
- arXiv: 2606.31732
- Reviewed arXiv version: v1
- DOI: 10.48550/arXiv.2606.31732
- Sources reviewed: 2026-10-20
- Added to the catalog: 2026-10-20
- Original paper: <https://arxiv.org/abs/2606.31732>
- PDF: <https://arxiv.org/pdf/2606.31732v1>
- Code: <https://github.com/JimmyZhengyz/unicoder>
- BibTeX: <https://awesomerea.org/papers/citations/paper-unicoder.bib>
- Catalog page: <https://awesomerea.org/papers/paper-unicoder/>
- Record JSON: <https://awesomerea.org/papers/paper-unicoder/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-unicoder/index.md)

## Scope and limitations

Experiments concern static visual reconstruction with one 8B backbone, including Design2Code and ScreenBench. Reference code is used during training; successful rendering does not prove interactive behavior. Extending the attribute extractor to new domains requires new schemas/prompts. Interactive interfaces, animation and mobile-app behavior are not evaluated.

## Why it fits this collection

Explores training signals for recovering code from visual website references.

## Publication and review notes

At 2844ebd, the repository releases ChartMimic/UniSVG evaluation wrappers, not model weights, full training code or datasets. Original repository code is Apache-2.0; adapted benchmarks retain their own terms. The arXiv title includes “UniCoder”; the HTML heading and software citation omit that prefix.

## Primary sources

1. <https://arxiv.org/abs/2606.31732v1>
2. <https://arxiv.org/html/2606.31732v1>
3. <https://github.com/JimmyZhengyz/unicoder/blob/2844ebd5908d563338580b1bd60f61032bf8fc24/README.md>
4. <https://github.com/JimmyZhengyz/unicoder/blob/2844ebd5908d563338580b1bd60f61032bf8fc24/MODEL_RELEASE.md>
5. <https://github.com/JimmyZhengyz/unicoder/blob/2844ebd5908d563338580b1bd60f61032bf8fc24/LICENSE>
6. <https://github.com/JimmyZhengyz/unicoder/blob/2844ebd5908d563338580b1bd60f61032bf8fc24/THIRD_PARTY_NOTICES.md>

## About this entry

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.
Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.