SketchVLM：视觉语言模型可以注释图像以解释思路并引导用户
SketchVLM: Vision language models can annotate images to explain thoughts and guide users
AI总结：
SketchVLM通过生成可编辑的SVG叠加图提升视觉推理和绘图任务的准确性与注释质量，实现高达28.5%的精度提升和1.48倍的注释质量提升。
摘要：
当回答图像相关问题时，人类会自然地指认、标注和绘制以解释其推理过程。相比之下，现代视觉语言模型（如Gemini-3-Pro和GPT-5）只能通过文本回应，这可能使用户难以验证。我们提出了SketchVLM，一个无需训练且模型无关的框架，使VLM能够生成非破坏性的、可编辑的SVG叠加图以可视化解释其答案。在七个涵盖视觉推理（迷宫导航、球下落轨迹预测和物体计数）和绘图（部分标注、连点成线和围绕物体绘制形状）的基准测试中，SketchVLM在视觉推理任务的准确性上提升了最高28.5个百分点，在注释质量上相对图像编辑和微调的草图基线提升了1.48倍，同时生成的注释更忠实于模型所陈述的答案。我们发现单轮生成已能实现较强的准确性和注释质量，而多轮生成则进一步拓展了人机协作的机会。一个交互式演示和代码可在https://sketchvlm.github.io/上找到。
英文摘要：
When answering questions about images, humans naturally point, label, and draw to explain their reasoning. In contrast, modern vision-language models (VLMs) such as Gemini-3-Pro and GPT-5 only respond with text, which can be difficult for users to verify. We present SketchVLM, a training-free, model-agnostic framework that enables VLMs to produce non-destructive, editable SVG overlays on the input image to visually explain their answers. Across seven benchmarks spanning visual reasoning (maze navigation, ball-drop trajectory prediction, and object counting) and drawing (part labeling, connecting-the-dots, and drawing shapes around objects), SketchVLM improves visual reasoning task accuracy by up to +28.5 percentage points and annotation quality by up to 1.48x relative to image-editing and fine-tuned sketching baselines, while also producing annotations that are more faithful to the model's stated answer. We find that single-turn generation already achieves strong accuracy and annotation quality, and multi-turn generation opens up further opportunities for human-AI collaboration. An interactive demo and code are at https://sketchvlm.github.io/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
