<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>生成建模 on Yiwen Cai</title><link>https://yiwen-cai.github.io/tags/%E7%94%9F%E6%88%90%E5%BB%BA%E6%A8%A1/</link><description>Recent content in 生成建模 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, 01 Sep 2026 15:08:24 +0800</lastBuildDate><atom:link href="https://yiwen-cai.github.io/tags/%E7%94%9F%E6%88%90%E5%BB%BA%E6%A8%A1/index.xml" rel="self" type="application/rss+xml"/><item><title>MIT 6.S184: Flow Matching and Diffusion Models — 第 1 章：生成建模即采样</title><link>https://yiwen-cai.github.io/notes/diffusion/generative-modeling/</link><pubDate>Tue, 01 Sep 2026 00:00:00 +0000</pubDate><author>caiyiwen.cs@foxmail.com (Yiwen Cai)</author><guid>https://yiwen-cai.github.io/notes/diffusion/generative-modeling/</guid><description>生成建模的核心任务不是寻找唯一的「最佳答案」，而是学习一个未知的数据分布并从中采样：把图像、视频、分子统一表示为向量，用有限数据集逼近 p_data，并区分无条件生成与条件生成。</description></item><item><title>MIT 6.S184: Flow Matching and Diffusion Models — 第 2 章：流模型与扩散模型</title><link>https://yiwen-cai.github.io/notes/diffusion/flow-and-diffusion-models/</link><pubDate>Tue, 01 Sep 2026 00:00:00 +0000</pubDate><author>caiyiwen.cs@foxmail.com (Yiwen Cai)</author><guid>https://yiwen-cai.github.io/notes/diffusion/flow-and-diffusion-models/</guid><description>深入解析连续时间生成模型的基础范式：从向量场定义、ODE 与 Flow 映射，到布朗运动、SDE 随机动力学及数值模拟（Euler 与 Euler-Maruyama 方法），建立确定性流与随机扩散的统一视角。</description></item></channel></rss>