<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Architecture on C.CUI's Log</title><link>https://cuicaihao.github.io/tags/architecture/</link><description>Recent content in Architecture on C.CUI's Log</description><generator>Hugo</generator><language>en-AU</language><lastBuildDate>Sun, 03 May 2026 09:05:02 +1000</lastBuildDate><atom:link href="https://cuicaihao.github.io/tags/architecture/index.xml" rel="self" type="application/rss+xml"/><item><title>Deep Decoding: How Large Language Models 'See' Structure?</title><link>https://cuicaihao.github.io/posts/2026-05-03-how-llms-see-structure/</link><pubDate>Sun, 03 May 2026 09:05:02 +1000</pubDate><guid>https://cuicaihao.github.io/posts/2026-05-03-how-llms-see-structure/</guid><description>Explore the architectural differences between Native Multimodal, MoE, and Long Context LLMs, and how they perceive and process structural information in professional workflows.</description></item></channel></rss>