mlsanityData to 14 Oct 2026

SVGen: Interpretable Vector Graphics Generation with Large Language Models

arXiv 2508.09168 ↗First posted 6 Aug 2025cs.LG cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ideas into precise vector graphics remains a time-consuming challenge. To address this, we introduce SVG-1M, a large-scale dataset of high-quality SVGs paired with natural language descriptions. Through advanced data augmentation and annotation, we create well-aligned Text to SVG training pairs, including a subset with Chain of Thought annotations for enhanced semantic guidance. Based on this dataset, we propose SVGen, an end-to-end model that generates SVG code from natural language inputs. Our approach ensures semantic accuracy and structural completeness, supported by curriculum learning and reinforcement learning optimization. Experiments show that SVGen outperforms general large models and traditional rendering methods in both effectiveness and efficiency. Code, model, and dataset are available on GitHub.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 23 of its 53 references that are in the map. First posted on arXiv 6 Aug 2025.

Builds on

23 of 53 references.

References · 23

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023BloombergGPT: A Large Language Model for Financecited by 939
  5. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 502
  6. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 287
  7. 2021CLIPDraw: Exploring Text-to-Drawing Synthesis through Language-Image Encoderscited by 187
  8. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 159
  9. 2023DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Servicescited by 120
  10. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 116
  11. 2023AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZcited by 79
  12. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Modelcited by 76
11 more
  1. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 75
  2. 2024Empowering LLMs to Understand and Generate Complex Vector Graphicscited by 66
  3. 2022CLIPasso: Semantically-Aware Object Sketchingcited by 57
  4. 2019FIGR: Few-shot Image Generation with Reptilecited by 56
  5. 2023DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Modelscited by 54
  6. 2024Text-to-Vector Generation with Neural Path Representationcited by 33
  7. 2020P-Cloth: Interactive Complex Cloth Simulation on Multi-GPU Systems using Dynamic Matrix Assembly and Pipelined Implicit Integratorscited by 26
  8. 2023FigGen: Text to Scientific Figure Generationcited by 17
  9. 2024NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generationcited by 17
  10. 2021DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learningcited by 15
  11. 2024SVGBuilder: Component-Based Colored SVG Generation with Text-Guided Autoregressive Transformerscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 13.

14 papers.

Sort:

By area:

  1. 2026Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedbackcited by 12
  2. 2026VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animationcited by 6
  3. 2026Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestrationcited by 5
  4. 2026Seeing is Improving: Visual Feedback for Iterative Text Layout Refinementcited by 4
  5. 2025PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMscited by 3
  6. 2026AmodalSVG: Amodal Image Vectorization via Semantic Layer Peelingcited by 3
  7. 2026GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generationcited by 2
  8. 2026Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modelingcited by 1
  9. 2026Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysiscited by 1
  10. 2026A Scalable Vector Graphics Latent Spacecited by 1
  11. 2026From Tokens to Numbers: Continuous Number Modeling for SVG Generationcited by 0
  12. 2026GenTI: Benchmarking LLMs for Autonomous IDPS Rule Generation for Unseen Attackscited by 0
2 more
  1. 2026CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generationcited by 0
  2. 2026SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation
  2. 2026VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing
  3. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
  4. 2025SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation
  5. 2025UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
  6. 2026IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework
  7. 2023Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Models
  8. 2025OmniSVG: A Unified Scalable Vector Graphics Generation Model