<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>生成模型 on Yiwen Cai</title><link>https://yiwen-cai.github.io/tags/%E7%94%9F%E6%88%90%E6%A8%A1%E5%9E%8B/</link><description>Recent content in 生成模型 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>Fri, 11 Sep 2026 17:20:09 +0800</lastBuildDate><atom:link href="https://yiwen-cai.github.io/tags/%E7%94%9F%E6%88%90%E6%A8%A1%E5%9E%8B/index.xml" rel="self" type="application/rss+xml"/><item><title>MIT 6.S184: Flow Matching and Diffusion Models — 第 4 章：Score 函数与 Score Matching</title><link>https://yiwen-cai.github.io/notes/diffusion/score-based-diffusion/</link><pubDate>Fri, 11 Sep 2026 00:00:00 +0000</pubDate><author>caiyiwen.cs@foxmail.com (Yiwen Cai)</author><guid>https://yiwen-cai.github.io/notes/diffusion/score-based-diffusion/</guid><description>从条件 score 的后验平均出发，推导高斯路径下 score、去噪器与速度场的转换，用 Fokker–Planck 方程解释如何给 ODE 加噪而保持边缘分布，并将 score matching 化为噪声回归。</description></item><item><title>MIT 6.S184: Flow Matching and Diffusion Models — 第 3 章：流匹配</title><link>https://yiwen-cai.github.io/notes/diffusion/flow-matching/</link><pubDate>Wed, 02 Sep 2026 00:00:00 +0000</pubDate><author>caiyiwen.cs@foxmail.com (Yiwen Cai)</author><guid>https://yiwen-cai.github.io/notes/diffusion/flow-matching/</guid><description>Flow Matching 通过回归可解析的条件向量场，间接学到边缘向量场，实现 simulation-free 训练。涵盖条件概率路径、边缘化技巧、连续性方程与 Gaussian CondOT 的完整推导。</description></item></channel></rss>