<?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>music-generation on Sparse Notes</title>
    <link>https://sparsenotes.com/tags/music-generation/</link>
    <description>Recent content in music-generation on Sparse Notes</description>
    <image>
      <url>https://sparsenotes.com/images/og-default.png</url>
      <link>https://sparsenotes.com/images/og-default.png</link>
    </image>
    <generator>Hugo -- gohugo.io</generator>
    <lastBuildDate>Sat, 14 Nov 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://sparsenotes.com/tags/music-generation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Self-Attention for Generative Models (Ashish Vaswani &amp; Anna Huang, Stanford CS224N, 2019)</title>
      <link>https://sparsenotes.com/posts/2026/11/self-attention-generative-models-vaswani-huang/</link>
      <pubDate>Sat, 14 Nov 2026 00:00:00 +0000</pubDate>
      
      <guid>https://sparsenotes.com/posts/2026/11/self-attention-generative-models-vaswani-huang/</guid>
      <description>Two years after &amp;#39;Attention Is All You Need&amp;#39;, Transformer co-author Ashish Vaswani explains to a Stanford class why self-attention works and what it costs, and Anna Huang shows how relative attention let the Music Transformer keep a motif going past its training length.</description>
    </item>
    
  </channel>
</rss>
