<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Svg on Vincent</title><link>https://tardfyou.github.io/tags/svg/</link><description>Recent content in Svg on Vincent</description><generator>Hugo</generator><language>en-US</language><managingEditor>3143596095@qq.com (Tardfyou)</managingEditor><webMaster>3143596095@qq.com (Tardfyou)</webMaster><copyright>Tardfyou</copyright><lastBuildDate>Fri, 24 Apr 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://tardfyou.github.io/tags/svg/index.xml" rel="self" type="application/rss+xml"/><item><title>How to Make High-End, Editable Research Figures with AI</title><link>https://tardfyou.github.io/posts/ai-editable-research-figures/</link><pubDate>Fri, 24 Apr 2026 00:00:00 +0800</pubDate><author>3143596095@qq.com (Tardfyou)</author><guid>https://tardfyou.github.io/posts/ai-editable-research-figures/</guid><description>The strongest current workflow for academic figures is hybrid: use a multimodal LLM as a prompt compiler, use image models for style and visual polish, and finish the deliverable as SVG, HTML, Mermaid, Typst, or Office-native assets.</description></item></channel></rss>