<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>CTMC on Yiwen Cai</title><link>https://yiwen-cai.github.io/tags/ctmc/</link><description>Recent content in CTMC on Yiwen Cai</description><generator>Hugo -- gohugo.io</generator><language>zh-cn</language><managingEditor>caiyiwen.cs@foxmail.com (Yiwen Cai)</managingEditor><webMaster>caiyiwen.cs@foxmail.com (Yiwen Cai)</webMaster><copyright>© 2026 Yiwen Cai</copyright><lastBuildDate>Tue, 03 Nov 2026 15:44:47 +0800</lastBuildDate><atom:link href="https://yiwen-cai.github.io/tags/ctmc/index.xml" rel="self" type="application/rss+xml"/><item><title>MIT 6.S184: Flow Matching and Diffusion Models — 第 7 章：离散扩散模型：用 CTMC 构建语言模型</title><link>https://yiwen-cai.github.io/notes/diffusion/discrete-diffusion/</link><pubDate>Tue, 03 Nov 2026 00:00:00 +0000</pubDate><author>caiyiwen.cs@foxmail.com (Yiwen Cai)</author><guid>https://yiwen-cai.github.io/notes/diffusion/discrete-diffusion/</guid><description>用连续时间马尔可夫链（CTMC）的跳转速率把简单离散分布逐步演变为文本分布：从速率矩阵、小步 Euler 转移与因子化 CTMC 出发，经条件混合路径、Kolmogorov Forward Equation 与后验加权边缘化，将 Discrete Flow Matching 与掩码扩散语言模型（MDLM）的训练化为逐位置干净 token 的交叉熵分类问题。</description></item></channel></rss>