AutoFigure-Edit: Generating Editable Scientific Illustration
About
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/.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Illustration Generation | FigureBench | Aesthetic8.32 | 7 | |
| Raster-to-SVG conversion | 80 CRAFTER outputs (test) | Position Score6.92 | 5 | |
| SVG Generation | SVG Generation (test) | RSR91.5 | 3 |