mlsanityData to 7 Oct 2026

StarVector: Generating Scalable Vector Graphics Code from Images and Text

arXiv 2312.11556 ↗First posted 17 Dec 2023cs.CV cs.AI cs.CLcited by 96

Not on the map. Why?

Cited by 20 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectorization, lacking semantic understanding, often producing artifacts, and struggling with SVG primitives beyond path curves. To address these issues, we introduce StarVector, a multimodal large language model for SVG generation. It performs image vectorization by understanding image semantics and using SVG primitives for compact, precise outputs. Unlike traditional methods, StarVector works directly in the SVG code space, leveraging visual understanding to apply accurate SVG primitives. To train StarVector, we create SVG-Stack, a diverse dataset of 2M samples that enables generalization across vectorization tasks and precise use of primitives like ellipses, polygons, and text. We address challenges in SVG evaluation, showing that pixel-based metrics like MSE fail to capture the unique qualities of vector graphics. We introduce SVG-Bench, a benchmark across 10 datasets, and 3 tasks: Image-to-SVG, Text-to-SVG generation, and diagram generation. Using this setup, StarVector achieves state-of-the-art performance, producing more compact and semantically rich SVGs.

Key facts. Cited by 96 papers in the map (data through 7 Oct 2026). Builds on 59 of its 99 references that are in the map. First posted on arXiv 17 Dec 2023.

Builds on

59 of 99 references.

References · 59

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  7. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  8. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  9. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  10. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  11. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  12. 2023Visual Instruction Tuningcited by 7,792
38 more
  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2016Layer Normalizationcited by 5,579
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  8. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  10. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  11. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  12. 2022A ConvNet for the 2020scited by 3,545
  13. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  14. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  15. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  16. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  17. 2015VQA: Visual Question Answeringcited by 2,489
  18. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,346
  19. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  20. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
  21. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  22. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 876
  23. 2023StarCoder: may the source be with you!cited by 790
  24. 2019Fast Transformer Decoding: One Write-Head is All You Needcited by 700
  25. 2019CodeSearchNet Challenge: Evaluating the State of Semantic Code Searchcited by 638
  26. 2022The Stack: 3 TB of permissively licensed source codecited by 354
  27. 2016Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Modelscited by 299
  28. 2015A note on the evaluation of generative modelscited by 291
  29. 2022mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connectionscited by 185
  30. 2023SantaCoder: don't reach for the stars!cited by 169
  31. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  32. 2023Accelerating LLM Inference with Staged Speculative Decodingcited by 151
  33. 2022GitHub Copilot AI pair programmer: Asset or Liability?cited by 150
  34. 2018Correcting Length Bias in Neural Machine Translationcited by 119
  35. 2021Im2Vec: Synthesizing Vector Graphics without Vector Supervisioncited by 114
  36. 2017pix2code: Generating Code from a Graphical User Interface Screenshotcited by 113
  37. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Modelscited by 112
  38. 2019A Learned Representation for Scalable Vector Graphicscited by 91

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 28; 2026: 64.

96 papers.

Sort:

By area:

  1. 2025AutoPresent: Designing Structured Visuals from Scratchcited by 63
  2. 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agentscited by 60
  3. 2025StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputscited by 23
  4. 2025SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Designcited by 22
  5. 2026AutoFigure: Generating and Refining Publication-Ready Scientific Illustrationscited by 20
  6. 2025Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generationcited by 18
  7. 2025VinciCoder: Unifying Multimodal Code Generation via Coarse-to-fine Visual Reinforcement Learningcited by 18
  8. 2025WebMMU: A Benchmark for Multimodal Multilingual Website Understanding and Code Generationcited by 16
  9. 2025VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representationcited by 15
  10. 2024Visually Descriptive Language Model for Vector Graphics Reasoningcited by 14
  11. 2025Draw with Thought: Unleashing Multimodal Reasoning for Scientific Diagram Generationcited by 14
  12. 2024LitLLMs, LLMs for Literature Review: Are we there yet?cited by 12
38 more
  1. 2025InternSVG: Towards Unified SVG Tasks with Multimodal Large Language Modelscited by 12
  2. 2026AutoFigure-Edit: Generating Editable Scientific Illustrationcited by 12
  3. 2026Multimodal OCR: Parse Anything from Documentscited by 12
  4. 2026Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedbackcited by 12
  5. 2025Reinforcement Learning for Large Model: A Surveycited by 8
  6. 2025SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generationcited by 8
  7. 2025Octopus: Agentic Multimodal Reasoning with Six-Capability Orchestrationcited by 8
  8. 2026EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detectioncited by 8
  9. 2025AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understandingcited by 7
  10. 2026VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generationcited by 7
  11. 2025Symbolic Graphics Programming with Large Language Modelscited by 6
  12. 2025DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidancecited by 6
  13. 2026SciFig: Towards Automating Editable Figure Generation for Scientific Paperscited by 6
  14. 2026VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animationcited by 6
  15. 2025LLM Code Customization with Visual Results: A Benchmark on TikZcited by 5
  16. 2025BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Executioncited by 5
  17. 2026Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestrationcited by 5
  18. 2026VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editingcited by 5
  19. 2026LottieGPT: Tokenizing Vector Animation for Autoregressive Generationcited by 5
  20. 2025VectorEdits: A Dataset and Benchmark for Instruction-Based Editing of Vector Graphicscited by 4
  21. 2026MM-ReCoder: Advancing Chart-to-Code Generation with Reinforcement Learning and Self-Correctioncited by 4
  22. 2024CraftSVG: Multi-Object Text-to-SVG Synthesis via Layout Guided Diffusioncited by 3
  23. 2025VisCoder2: Building Multi-Language Visualization Coding Agentscited by 3
  24. 2026VisPhyWorld: Probing Physical Reasoning via Code-Driven Video Reconstructioncited by 3
  25. 2026VecGlypher: Unified Vector Glyph Generation with Language Modelscited by 3
  26. 2026AmodalSVG: Amodal Image Vectorization via Semantic Layer Peelingcited by 3
  27. 2025AutoSketch: VLM-assisted Style-Aware Vector Sketch Completioncited by 2
  28. 2025StarFlow: Generating Structured Workflow Outputs From Sketch Imagescited by 2
  29. 2026TechING: Towards Real World Technical Image Understanding via VLMscited by 2
  30. 2026SVRepair: Structured Visual Reasoning for Automated Program Repaircited by 2
  31. 2026OmniLottie: Generating Vector Animations via Parameterized Lottie Tokenscited by 2
  32. 2026Visual-ERM: Reward Modeling for Visual Equivalencecited by 2
  33. 2026Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMscited by 2
  34. 2026GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Modelscited by 2
  35. 2026GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generationcited by 2
  36. 2024SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generationcited by 1
  37. 2025SVGauge: Towards Human-Aligned Evaluation for SVG Generationcited by 1
  38. 2025MultiMat: Multimodal Program Synthesis for Procedural Materials using Large Multimodal Modelscited by 1

50 most cited of 96 All 96 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
  2. 2025SVGen: Interpretable Vector Graphics Generation with Large Language Models
  3. 2025OmniSVG: A Unified Scalable Vector Graphics Generation Model
  4. 2026VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models
  5. 2025UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
  6. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Model
  7. 2025SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation
  8. 2024VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation