AutoFigure-Edit: Generating Editable Scientific Illustration

2026-03-03

AI Summary

Existing methods for scientific illustration generation suffer from limitations in editability, style controllability, and computational efficiency. This work proposes the first end-to-end system capable of directly generating fully editable SVG illustrations from long-form scientific texts, while supporting reference-image-guided style transfer. By integrating long-context language understanding, image-driven style control, and native SVG synthesis, the approach enables high-quality, efficient, and interactively friendly illustration creation. The contributions include publicly released source code, an online demo platform, and accompanying tutorial videos, collectively enhancing the flexibility and productivity of scientific visualization workflows.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Computer Vision: Computational Photography, Image & Video Synthesis
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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/.

Problem

• scientific illustration
• editability
• stylistic controllability
• automated generation

Innovation

• editable scientific illustration
• reference-guided styling
• long-context understanding
• SVG editing
• end-to-end generation