<?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>Low-Rank Adaptation on DiggingPapers</title>
    <link>https://diggingpapers.github.io/tags/low-rank-adaptation/</link>
    <description>Recent content in Low-Rank Adaptation on DiggingPapers</description>
    <generator>Hugo -- 0.154.5</generator>
    <language>ko-kr</language>
    <lastBuildDate>Wed, 26 Nov 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://diggingpapers.github.io/tags/low-rank-adaptation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Evolution Strategies at the Hyperscale</title>
      <link>https://diggingpapers.github.io/posts/learning_strategy/eggroll/</link>
      <pubDate>Wed, 26 Nov 2025 00:00:00 +0000</pubDate>
      <guid>https://diggingpapers.github.io/posts/learning_strategy/eggroll/</guid>
      <description>Evolution Strategies(ES)라는 학습 방식은 forward pass만으로 학습 가능한 강력한 알고리즘인데, 실질적으로 LLM과 같은 huge model에는 적용이 불가능한 limitation을 해결하고자 제안.</description>
    </item>
  </channel>
</rss>
