<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Generative Modelling on Kaushik's Portfolio</title><link>https://kauuu.github.io/topics/generative-modelling/</link><description>Recent content in Generative Modelling on Kaushik's Portfolio</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Thu, 06 Nov 2025 22:43:32 +0100</lastBuildDate><atom:link href="https://kauuu.github.io/topics/generative-modelling/index.xml" rel="self" type="application/rss+xml"/><item><title>Diffusion Models: An Intuitive Understanding</title><link>https://kauuu.github.io/posts/diffusion-model/</link><pubDate>Thu, 06 Nov 2025 22:43:32 +0100</pubDate><guid>https://kauuu.github.io/posts/diffusion-model/</guid><description>&lt;p&gt;&lt;strong&gt;Disclaimer&lt;/strong&gt;: This post is my notes on understanding diffusion models from an intuitive perspective. It is not a formal explanation, and I might have made mistakes. Please reach out to me if you find any errors!&lt;/p&gt;
&lt;h1 id="introduction"&gt;Introduction&lt;/h1&gt;
&lt;p&gt;The original paper was from UC Berkley and went by the name &lt;em&gt;Denoising Diffusion Probabilistic Model&lt;/em&gt;.&lt;/p&gt;
&lt;p&gt;The original idea might sound counter-intuitive, but it takes a random noise and transforms it into a realistic image &lt;em&gt;step-by-step&lt;/em&gt;.&lt;/p&gt;</description></item></channel></rss>