<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>State Space on WorldSense Tech Blog</title><link>https://worldsensetech.com/en/tags/state-space/</link><description>Recent content in State Space on WorldSense Tech Blog</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Sun, 02 Aug 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://worldsensetech.com/en/tags/state-space/index.xml" rel="self" type="application/rss+xml"/><item><title>Deep Dive into RSSM: The Core Engine of World Models</title><link>https://worldsensetech.com/en/articles/rssm-deep-dive/</link><pubDate>Sun, 02 Aug 2026 00:00:00 +0000</pubDate><guid>https://worldsensetech.com/en/articles/rssm-deep-dive/</guid><description>&lt;p&gt;In the previous article, we covered the basic concepts of world models and the overall architecture of DreamerV3. Some readers asked for a deeper explanation of how RSSM actually works. This article dissects the core component of the Dreamer family of world models.&lt;/p&gt;
&lt;p&gt;I&amp;rsquo;ll try to make the math clear without being overly formal. After all, our goal is to understand the principles, not prove theorems.&lt;/p&gt;
&lt;h2 id="why-we-need-state-space-models"&gt;Why We Need State-Space Models&lt;/h2&gt;
&lt;p&gt;Before discussing RSSM, let&amp;rsquo;s step back and ask: why do we need state-space models at all? Can&amp;rsquo;t we just use an RNN or Transformer directly?&lt;/p&gt;</description></item></channel></rss>