# VecFontLLM: Anchor-Guided Direct Synthesis of Chinese Vector Fonts

arXiv: https://arxiv.org/abs/2607.17251 · HTML: https://mlsanity.com/paper/2607.17251/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 62 references that are in the map.
- First posted on arXiv 19 Jul 2026.

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Visual Transformers: Token-based Image Representation and Processing for Computer Vision](https://mlsanity.com/paper/2006.03677/) (2020)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [Scalable Best-of-N Selection for Large Language Models via Self-Certainty](https://mlsanity.com/paper/2502.18581/) (2025)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [A Learned Representation for Scalable Vector Graphics](https://mlsanity.com/paper/1904.02632/) (2019)
- [PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model](https://mlsanity.com/paper/2510.14528/) (2025)
- [SVGDreamer: Text Guided SVG Generation with Diffusion Model](https://mlsanity.com/paper/2312.16476/) (2023)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [FontDiffuser: One-Shot Font Generation via Denoising Diffusion with Multi-Scale Content Aggregation and Style Contrastive Learning](https://mlsanity.com/paper/2312.12142/) (2023)
- [Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts](https://mlsanity.com/paper/2104.00887/) (2021)
- [Few-shot Compositional Font Generation with Dual Memory](https://mlsanity.com/paper/2005.10510/) (2020)
- [Rendering-Aware Reinforcement Learning for Vector Graphics Generation](https://mlsanity.com/paper/2505.20793/) (2025)
- [Text-to-Vector Generation with Neural Path Representation](https://mlsanity.com/paper/2405.10317/) (2024)
- [DeepVecFont-v2: Exploiting Transformers to Synthesize Vector Fonts with Higher Quality](https://mlsanity.com/paper/2303.14585/) (2023)
- [SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities](https://mlsanity.com/paper/2404.13710/) (2024)
- [ZiGAN: Fine-grained Chinese Calligraphy Font Generation via a Few-shot Style Transfer Approach](https://mlsanity.com/paper/2108.03596/) (2021)
- [VecFusion: Vector Font Generation with Diffusion](https://mlsanity.com/paper/2312.10540/) (2023)
- [StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding](https://mlsanity.com/paper/2012.08687/) (2020)
- [NIVeL: Neural Implicit Vector Layers for Text-to-Vector Generation](https://mlsanity.com/paper/2405.15217/) (2024)
- [DualVector: Unsupervised Vector Font Synthesis with Dual-Part Representation](https://mlsanity.com/paper/2305.10462/) (2023)
- [SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation](https://mlsanity.com/paper/2509.24299/) (2025)

## Abstract (arXiv)

Direct generation of Chinese vector fonts is a challenging and ongoing problem. A Chinese vector glyph contains complex component structure, anchor layout, and B'ezier curve details, which work at different scales, but a standard vector sequence writes them together in one long sequence, making the task of vector font synthesis challenging. Existing direct vector generators often fail on complex characters, while raster-domain methods must vectorize the synthesized glyph images afterward. To address the above-mentioned problem, this paper proposes VecFontLLM, an anchor-guided multimodal large language model for direct few-shot synthesis of Chinese vector fonts. Our key idea is to generate vector glyphs through anchors rather than a standard vector sequence. Specifically, the proposed VecFontLLM first predicts and refines an anchor scaffold that fixes the coarse layout of components and contours, and then completes B'ezier control points to recover local curvature and style. At test time, a confidence-guided generation chain samples multiple component candidates and continues synthesis from the highest-confidence one, improving stability for complex glyphs. This work demonstrates, for the first time, high-quality few-shot synthesis of complex Chinese vector glyphs directly in the vector domain, without raster generation or vectorization. Experiments on several Chinese font datasets show substantial improvements over existing vector font synthesis methods, competitive glyph rendering quality against raster-domain baselines, and vector command distributions close to real fonts.