Research map / Image generation / Text-to-image diffusion
AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
Minjun Zhu, Zhen Lin, Yixuan Weng, Panzhong Lu, Qiujie Xie, Yifan Wei, Sifan Liu, QiYao Sun, Yue Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use AutoFigure instead of best code baseline | scientific illustration generation · FigureBench Paper | Overall score: 6.35 -> 7.03 | Improved |
| use AutoFigure instead of SVG-Code | scientific illustration generation · FigureBench Blog | Win-Rate vs reference: 45.0% -> 75.0% | Improved |
| use AutoFigure instead of Gemini-SVG | scientific illustration generation · FigureBench Textbook | Win-Rate vs reference: 76.9% -> 97.5% | Improved |
| add critique-and-refine iterations (0 to 5) (ablation) | AutoFigure · FigureBench | Overall score: 6.28 -> 7.14 | Improved |
| add final rendering stage after the symbolic layout (ablation) | AutoFigure with GPT-5 · FigureBench | Overall score: 6.38 -> 7.480 | Improved |
| use SVG intermediate format instead of PPT (ablation) | AutoFigure · FigureBench | Overall score: 6.12 -> 8.98 | Improved |
| use HTML intermediate format instead of PPT (ablation) | AutoFigure · FigureBench | Overall score: 6.12 -> 8.85 | Improved |
| use Qwen3-VL-235B backbone instead of GLM-4.5V (ablation) | AutoFigure · FigureBench | Overall score: 5.99 -> 7.08 | Improved |
| use GPT-5 backbone instead of Qwen3-VL-235B (ablation) | AutoFigure · FigureBench | Overall score: 7.08 -> 7.48 | Improved |
| use Qwen3-VL-235B backbone instead of Gemini-2.5-Pro (ablation) | AutoFigure · FigureBench | Overall score: 6.99 -> 7.08 | Improved |
Closest papers by meaning
- P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark (ICLR 2026 · similarity 0.86)
- Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers (NeurIPS 2025 · similarity 0.86)
- AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ (ICLR 2024 · similarity 0.85)
- DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ (NeurIPS 2024 · similarity 0.85)
- AutoPresent: Designing Structured Visuals from Scratch (CVPR 2025 · similarity 0.84)
- Factuality Matters: When Image Generation and Editing Meet Structured Visuals (ICLR 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
