mlsanityData to 14 Oct 2026

AutoFigure-Edit: Generating Editable Scientific Illustration

arXiv 2603.06674 ↗First posted 3 Mar 2026cs.CV cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 13 of its 21 references that are in the map. First posted on arXiv 3 Mar 2026.

Builds on

13 of 21 references.

References · 13

  1. 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 777
  2. 2024Bilateral Reference for High-Resolution Dichotomous Image Segmentationcited by 112
  3. 2023StarVector: Generating Scalable Vector Graphics Code from Images and Textcited by 102
  4. 2024MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualizationcited by 102
  5. 2023AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZcited by 79
  6. 2017Learning to Infer Graphics Programs from Hand-Drawn Imagescited by 74
  7. 2025OmniSVG: A Unified Scalable Vector Graphics Generation Modelcited by 74
  8. 2024From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editingcited by 31
  9. 2025TikZero: Zero-Shot Text-Guided Graphics Program Synthesiscited by 24
  10. 2025SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Modelcited by 19
  11. 2026SciFig: Towards Automating Editable Figure Generation for Scientific Paperscited by 8
  12. 2025From Pixels to Paths: A Multi-Agent Framework for Editable Scientific Illustrationcited by 4
1 more
  1. 2025Leveraging Large Language Models For Scalable Vector Graphics Processing: A Reviewcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 14.

14 papers.

Sort:

By area:

  1. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  2. 2026Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputscited by 9
  3. 2026SciFigDetect: A Benchmark for AI-Generated Scientific Figure Detectioncited by 4
  4. 2026GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generationcited by 2
  5. 2026SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisionscited by 2
  6. 2026PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documentscited by 1
  7. 2026SciForma: Structure-Faithful Generation of Scientific Diagramscited by 1
  8. 2026DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editablecited by 1
  9. 2026EdiTikZ: Scientific Figure Editing from Revision Trajectoriescited by 1
  10. 2026GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Paperscited by 0
  11. 2026PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedbackcited by 0
  12. 2026VectorHarness: Recovering Editable, Relation-Preserving Structure from Scientific Graphicscited by 0
2 more
  1. 2026FigAct: Turning Scientific Figures into Active Canvases for Explanationcited by 0
  2. 2026One Figure, Every Canvas: Editable Flowchart Relayout via Agentic Pipelinecited by 0