mlsanityData to 7 Oct 2026

StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis

arXiv 2401.17093 ↗First posted 30 Jan 2024cs.CV cs.CLcited by 26

Not on the map. Why?

Abstract (arXiv)

To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes. This paper posits that an alternative representation of images, vector graphics, can effectively surmount this limitation by enabling a more natural and semantically coherent segmentation of the image information. Thus, we introduce StrokeNUWA, a pioneering work exploring a better visual representation ''stroke tokens'' on vector graphics, which is inherently visual semantics rich, naturally compatible with LLMs, and highly compressed. Equipped with stroke tokens, StrokeNUWA can significantly surpass traditional LLM-based and optimization-based methods across various metrics in the vector graphic generation task. Besides, StrokeNUWA achieves up to a 94x speedup in inference over the speed of prior methods with an exceptional SVG code compression ratio of 6.9%.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 32 of its 37 references that are in the map. First posted on arXiv 30 Jan 2024.

Builds on

32 of 37 references.

References · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2023GPT-4 Technical Reportcited by 18,132
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  6. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  7. 2017Neural Discrete Representation Learningcited by 4,650
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  10. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  12. 2023PaLM 2 Technical Reportcited by 1,154
20 more
  1. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  2. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
  3. 2020Jukebox: A Generative Model for Musiccited by 535
  4. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
  5. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 284
  6. 2021N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtioncited by 253
  7. 2020DeepSVG: A Hierarchical Generative Network for Vector Graphics Animationcited by 158
  8. 2023Emu: Generative Pretraining in Multimodalitycited by 156
  9. 2023Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Modelcited by 145
  10. 2022VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Modelscited by 112
  11. 2022Towards Layer-wise Image Vectorizationcited by 77
  12. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Modelcited by 75
  13. 2023IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformerscited by 73
  14. 2019FIGR: Few-shot Image Generation with Reptilecited by 54
  15. 2022Robust Semantic Communications with Masked VQ-VAE Enabled Codebookcited by 53
  16. 2023Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformerscited by 33
  17. 2014Stacked Quantizers for Compositional Vector Compressioncited by 30
  18. 2022Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformercited by 30
  19. 2022Aesthetic Text Logo Synthesis via Content-aware Layout Inferringcited by 19
  20. 2023Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 10; 2026: 8.

26 papers.

Sort:

By area:

  1. 2025OmniSVG: A Unified Scalable Vector Graphics Generation Modelcited by 71
  2. 2024Empowering LLMs to Understand and Generate Complex Vector Graphicscited by 63
  3. 2025LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformercited by 43
  4. 2024Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Modelscited by 36
  5. 2024Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Surveycited by 27
  6. 2024SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilitiescited by 25
  7. 2025SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generationcited by 16
  8. 2024Visually Descriptive Language Model for Vector Graphics Reasoningcited by 14
  9. 2026Render-in-the-Loop: Vector Graphics Generation via Visual Self-Feedbackcited by 12
  10. 2025Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawingscited by 9
  11. 2025Discrete Tokenization for Multimodal LLMs: A Comprehensive Surveycited by 7
  12. 2025DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidancecited by 6
14 more
  1. 2026VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animationcited by 6
  2. 2024Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervisioncited by 3
  3. 2025Leveraging Large Language Models For Scalable Vector Graphics Processing: A Reviewcited by 3
  4. 2025AutoSketch: VLM-assisted Style-Aware Vector Sketch Completioncited by 2
  5. 2025Style Customization of Text-to-Vector Generation with Image Diffusion Priorscited by 2
  6. 2026OmniLottie: Generating Vector Animations via Parameterized Lottie Tokenscited by 2
  7. 2024SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generationcited by 1
  8. 2026Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modelingcited by 1
  9. 2026mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrievalcited by 1
  10. 2024SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generationcited by 0
  11. 2025Bridging Vision, Language, and Mathematics: Pictographic Character Reconstruction with B'ezier Curvescited by 0
  12. 2026Draw This Firstcited by 0
  13. 2026CANVAS: Consistency-Aware Navigation via Visual Adaptive Sampling for Long-Context Text-to-SVG Generationcited by 0
  14. 2026SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generationcited by 0