<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>SVG Generation on SoloSoft</title><link>https://www.solosoft.dev/tags/svg-generation/</link><description>Recent content in SVG Generation on SoloSoft</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 01 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.solosoft.dev/tags/svg-generation/index.xml" rel="self" type="application/rss+xml"/><item><title>OmniSVG: Unified Multimodal SVG Generation Model (NeurIPS 2025)</title><link>https://www.solosoft.dev/post/omnisvg-generation-2026/</link><pubDate>Fri, 01 May 2026 00:00:00 +0000</pubDate><guid>https://www.solosoft.dev/post/omnisvg-generation-2026/</guid><description>&lt;p&gt;Vector graphics are everywhere &amp;ndash; from icons and logos to illustrations and data visualizations. But generating complex SVGs programmatically has remained a stubborn research challenge, with most approaches limited to simple geometric shapes or requiring extensive training data. &lt;strong&gt;OmniSVG&lt;/strong&gt;, published at NeurIPS 2025, breaks through these limitations by introducing the first unified family of end-to-end multimodal SVG generators built on vision-language models.&lt;/p&gt;
&lt;p&gt;The project at &lt;a href="https://github.com/OmniSVG/OmniSVG"&gt;github.com/OmniSVG/OmniSVG&lt;/a&gt; represents a paradigm shift in SVG generation. Rather than relying on differentiable rendering or reinforcement learning &amp;ndash; the dominant approaches prior to OmniSVG &amp;ndash; it fine-tunes pre-trained VLMs to output SVG code directly. This allows the model to leverage the vast visual knowledge encoded in modern VLMs while learning the syntax and structure of SVG as a target language.&lt;/p&gt;</description></item></channel></rss>