AutoFigure-Edit: Generating Editable Scientific Illustration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Zhen, Xie, Qiujie, Zhu, Minjun, Li, Shichen, Sun, Qiyao, Gu, Enhao, Ding, Yiran, Sun, Ke, Guo, Fang, Lu, Panzhong, Ning, Zhiyuan, Weng, Yixuan, Zhang, Yue
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908870769639424
author Lin, Zhen
Xie, Qiujie
Zhu, Minjun
Li, Shichen
Sun, Qiyao
Gu, Enhao
Ding, Yiran
Sun, Ke
Guo, Fang
Lu, Panzhong
Ning, Zhiyuan
Weng, Yixuan
Zhang, Yue
author_facet Lin, Zhen
Xie, Qiujie
Zhu, Minjun
Li, Shichen
Sun, Qiyao
Gu, Enhao
Ding, Yiran
Sun, Ke
Guo, Fang
Lu, Panzhong
Ning, Zhiyuan
Weng, Yixuan
Zhang, Yue
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06674
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AutoFigure-Edit: Generating Editable Scientific Illustration
Lin, Zhen
Xie, Qiujie
Zhu, Minjun
Li, Shichen
Sun, Qiyao
Gu, Enhao
Ding, Yiran
Sun, Ke
Guo, Fang
Lu, Panzhong
Ning, Zhiyuan
Weng, Yixuan
Zhang, Yue
Computer Vision and Pattern Recognition
Artificial Intelligence
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/.
title AutoFigure-Edit: Generating Editable Scientific Illustration
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.06674