DuetSVG：基于内部视觉引导的统一多模态SVG生成
DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance
将视觉预测作为解码时的内部引导信号，并配合测试时缩放策略，可迁移到其他需要结构化输出的多模态生成任务（如代码生成、布局生成）中，提升生成结果的几何一致性与视觉合理性。
原文依据 we apply a novel test-time scaling strategy that leverages the model's native visual predictions as guidance to improve SVG decoding quality
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期基于视觉语言模型（VLM）的方法在SVG生成上取得了令人印象深刻的结果。然而，由于它们仅生成文本且在解码过程中缺乏视觉信号，往往难以处理复杂语义，无法生成视觉上吸引人或几何一致的SVG。我们提出DuetSVG，一个统一的多模态模型，以端到端方式联合生成图像token和对应的SVG token。DuetSVG在图像和SVG数据集上训练。在推理时，我们采用一种新颖的测试时缩放策略，利用模型自身的视觉预测作为引导来提升SVG解码质量。大量实验表明，我们的方法优于现有方法，在广泛的应用中生成视觉忠实、语义对齐且语法干净的SVG。
英文原文摘要 835 字符
Recent vision-language model (VLM)-based approaches have achieved impressive results on SVG generation. However, because they generate only text and lack visual signals during decoding, they often struggle with complex semantics and fail to produce visually appealing or geometrically coherent SVGs. We introduce DuetSVG, a unified multimodal model that jointly generates image tokens and corresponding SVG tokens in an end-to-end manner. DuetSVG is trained on both image and SVG datasets. At inference, we apply a novel test-time scaling strategy that leverages the model's native visual predictions as guidance to improve SVG decoding quality. Extensive experiments show that our method outperforms existing methods, producing visually faithful, semantically aligned, and syntactically clean SVGs across a wide range of applications.