AutoFigure-Edit: Generating Editable Scientific Illustration

Zhen Lin, Qiujie Xie, Minjun Zhu, Shichen Li, Qiyao Sun +8 more
3/3/2026
cs.CVcs.AI

Official code: ResearAI/AutoFigure-Edit (4,133 stars, MIT, last commit 2026-04-30).

Abstract

High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable scientific illustrations from long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding, reference-guided styling, and native SVG editing, it enables efficient creation and refinement of high-quality scientific illustrations. To facilitate further progress in this field, we release the video at https://youtu.be/10IH8SyJjAQ, full codebase at https://github.com/ResearAI/AutoFigure-Edit and provide a website for easy access and interactive use at https://deepscientist.cc/.

View on arXivView PDF

Code Implementations(1)

ResearAI/AutoFigure-EditOfficial100%
MIT
4,133272CSS, HTMLFeb 3, 20265 months agoMIT

Similar Papers

AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations

89% match1 repo1.8k2026

PaperBanana: Automating Academic Illustration for AI Scientists

79% match3 repos7.2k2026

From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustration

79% match2025

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

76% match2026

Charts Are Not Images: On the Challenges of Scientific Chart Editing

76% match1 repo112025

SciFig: Towards Automating Scientific Figure Generation

76% match2026

Cite this paper

@article{lin2026autofigureedit,
  title  = {AutoFigure-Edit: Generating Editable Scientific Illustration},
  author = {Zhen Lin and Qiujie Xie and Minjun Zhu and Shichen Li and Qiyao Sun and Enhao Gu and Yiran Ding and Ke Sun and Fang Guo and Panzhong Lu and Zhiyuan Ning and Yixuan Weng and Yue Zhang},
  year   = {2026},
  eprint = {2603.06674},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.06674v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.06674.svg)](https://codeofpaper.com/paper/2603.06674)

Discussion