VecGlypher：基于语言模型的统一矢量字形生成
VecGlypher: Unified Vector Glyph Generation with Language Models
将矢量字形生成建模为自回归序列生成问题，直接输出SVG路径令牌，避免了栅格化中间步骤，为视觉生成任务提供了一种可编辑、高保真的矢量输出范式；其两阶段训练策略和坐标量化方法可迁移到其他结构化图形生成任务。
原文依据 VecGlypher autoregressively emits SVG path tokens, avoiding raster intermediates and producing editable, watertight outlines in one pass.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论矢量字形是数字排版的原子单元，然而大多数基于学习的流程仍依赖于精心整理的示例表和栅格到矢量的后处理，这限制了可访问性和可编辑性。我们提出VecGlypher，一个单一的多模态语言模型，可直接从文本描述或图像示例生成高保真矢量字形。给定风格提示、可选的参考字形图像和目标字符，VecGlypher自回归地输出SVG路径令牌，避免栅格中间表示，并一次性生成可编辑、封闭的轮廓。排版感知的数据与训练方案使这成为可能：(i) 在39K个含噪Envato字体上进行大规模延续训练阶段，以掌握SVG语法和长程几何结构，随后 (ii) 在2.5K个专家标注的Google字体上进行后训练，这些字体带有描述性标签和示例，以将语言和图像与几何对齐；预处理对坐标框架进行归一化、规范化路径、对字族去重，并对坐标进行量化以实现稳定的长序列解码。在跨字族的分布外评估中，VecGlypher在纯文本生成方面显著优于通用大语言模型和专门的矢量字体基线，而图像参考生成达到了最优性能，相比DeepVecFont-v2和DualVector有显著提升。消融实验表明，模型规模和两阶段方案至关重要，且绝对坐标序列化能获得最佳几何结构。VecGlypher通过让用户用文字或示例进行设计，降低了字体创建的门槛，并为未来的多模态设计工具提供了可扩展的基础。
英文原文摘要 1663 字符
Vector glyphs are the atomic units of digital typography, yet most learning-based pipelines still depend on carefully curated exemplar sheets and raster-to-vector postprocessing, which limits accessibility and editability. We introduce VecGlypher, a single multimodal language model that generates high-fidelity vector glyphs directly from text descriptions or image exemplars. Given a style prompt, optional reference glyph images, and a target character, VecGlypher autoregressively emits SVG path tokens, avoiding raster intermediates and producing editable, watertight outlines in one pass. A typography-aware data and training recipe makes this possible: (i) a large-scale continuation stage on 39K noisy Envato fonts to master SVG syntax and long-horizon geometry, followed by (ii) post-training on 2.5K expert-annotated Google Fonts with descriptive tags and exemplars to align language and imagery with geometry; preprocessing normalizes coordinate frames, canonicalizes paths, de-duplicates families, and quantizes coordinates for stable long-sequence decoding. On cross-family OOD evaluation, VecGlypher substantially outperforms both general-purpose LLMs and specialized vector-font baselines for text-only generation, while image-referenced generation reaches a state-of-the-art performance, with marked gains over DeepVecFont-v2 and DualVector. Ablations show that model scale and the two-stage recipe are critical and that absolute-coordinate serialization yields the best geometry. VecGlypher lowers the barrier to font creation by letting users design with words or exemplars, and provides a scalable foundation for future multimodal design tools.