mlsanityData to 14 Oct 2026

Stroke Modeling Enables Vectorized Character Generation with Large Vectorized Glyph Model

arXiv 2511.11119 ↗First posted 14 Nov 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Vectorized glyphs are widely used in poster design, network animation, art display, and various other fields due to their scalability and flexibility. In typography, they are often seen as special sequences composed of ordered strokes. This concept extends to the token sequence prediction abilities of large language models (LLMs), enabling vectorized character generation through stroke modeling. In this paper, we propose a novel Large Vectorized Glyph Model (LVGM) designed to generate vectorized Chinese glyphs by predicting the next stroke. Initially, we encode strokes into discrete latent variables called stroke embeddings. Subsequently, we train our LVGM via fine-tuning DeepSeek LLM by predicting the next stroke embedding. With limited strokes given, it can generate complete characters, semantically elegant words, and even unseen verses in vectorized form. Moreover, we release a new large-scale Chinese SVG dataset containing 907,267 samples based on strokes for dynamically vectorized glyph generation. Experimental results show that our model has scaling behaviors on data scales. Our generated vectorized glyphs have been validated by experts and relevant individuals.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 45 references that are in the map. First posted on arXiv 14 Nov 2025.

Builds on

33 of 45 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 2020Scaling Laws for Neural Language Modelscited by 6,586
  8. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  9. 2017Neural Discrete Representation Learningcited by 4,712
  10. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  11. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,598
  12. 2023A Survey of Large Language Modelscited by 2,576
21 more
  1. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  2. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  3. 2022Galactica: A Large Language Model for Sciencecited by 744
  4. 2024DeepSeek-VL: Towards Real-World Vision-Language Understandingcited by 733
  5. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  6. 2023Llemma: An Open Language Model For Mathematicscited by 388
  7. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212
  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. 2023StarVector: Generating Scalable Vector Graphics Code from Images and Textcited by 102
  12. 2019A Learned Representation for Scalable Vector Graphicscited by 91
  13. 2023SVGDreamer: Text Guided SVG Generation with Diffusion Modelcited by 76
  14. 2023ChatCounselor: A Large Language Models for Mental Health Supportcited by 44
  15. 2023DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Qualitycited by 27
  16. 2021DeepVecFont: Synthesizing High-quality Vector Fonts via Dual-modality Learningcited by 15
  17. 2023Beyond Pixels: Exploring Human-Readable SVG Generation for Simple Images with Vision Language Modelscited by 8
  18. 2023VecFontSDF: Learning to Reconstruct and Synthesize High-quality Vector Fonts via Signed Distance Functionscited by 7
  19. 2022SVG Vector Font Generation for Chinese Characters with Transformercited by 6
  20. 2024Exploring Mathematical Extrapolation of Large Language Models with Synthetic Datacited by 6
  21. 2023Contour Completion by Transformers and Its Application to Vector Font Datacited by 2

Built on by

Not cited yet.