Paper page - AutoFigure-Edit: Generating Editable Scientific Illustration

Source: https://huggingface.co/papers/2603.06674 Authors:

,

,

,

,

,

,

,

,

,

,

Abstract

AutoFigure-Edit is an end-to-end system that generates editable scientific illustrations from text descriptions and reference images, supporting flexible style adaptation and efficient refinement.

High-qualityscientific illustrationsare essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, anend-to-end systemthat generates fully editablescientific illustrationsfrom long-form scientific text while enabling flexible style adaptation through user-provided reference images. By combining long-context understanding,reference-guided styling, and nativeSVG editing, it enables efficient creation and refinement of high-qualityscientific 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 arXiv pageView PDFProject pageGitHub3.51kAdd to collection

Get this paper in your agent:

hf papers read 2603\.06674

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2603.06674 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2603.06674 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2603.06674 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.