<?xml version="1.0" encoding="utf-8" standalone="yes" ?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>tokenization | Lee DongWon</title>
    <link>https://moovingsloth.github.io/tag/tokenization/</link>
      <atom:link href="https://moovingsloth.github.io/tag/tokenization/index.xml" rel="self" type="application/rss+xml" />
    <description>tokenization</description>
    <generator>Wowchemy (https://wowchemy.com)</generator><language>en-us</language><lastBuildDate>Fri, 11 Jul 2025 00:00:00 +0000</lastBuildDate>
    <image>
      <url>https://moovingsloth.github.io/media/sloth-icon-512.png</url>
      <title>tokenization</title>
      <link>https://moovingsloth.github.io/tag/tokenization/</link>
    </image>
    
    <item>
      <title>Sampling from Your Language Model One Byte at a Time</title>
      <link>https://moovingsloth.github.io/publication/byte_sampler/</link>
      <pubDate>Fri, 11 Jul 2025 00:00:00 +0000</pubDate>
      <guid>https://moovingsloth.github.io/publication/byte_sampler/</guid>
      <description></description>
    </item>
    
    <item>
      <title>Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations</title>
      <link>https://moovingsloth.github.io/publication/broken_tokens/</link>
      <pubDate>Thu, 10 Jul 2025 00:00:00 +0000</pubDate>
      <guid>https://moovingsloth.github.io/publication/broken_tokens/</guid>
      <description></description>
    </item>
    
    <item>
      <title>SuperBPE: Space Travel for Language Models</title>
      <link>https://moovingsloth.github.io/publication/superbpe/</link>
      <pubDate>Wed, 09 Jul 2025 00:00:00 +0000</pubDate>
      <guid>https://moovingsloth.github.io/publication/superbpe/</guid>
      <description></description>
    </item>
    
  </channel>
</rss>
