<?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>Continual Adaptation on Atsushi Yanagisawa</title>
    <link>https://atsushiyanaigsawa768.github.io/mysite/en/tags/continual-adaptation/</link>
    <description>Recent content in Continual Adaptation on Atsushi Yanagisawa</description>
    <generator>Hugo -- 0.147.0</generator>
    <language>en</language>
    <lastBuildDate>Wed, 13 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://atsushiyanaigsawa768.github.io/mysite/en/tags/continual-adaptation/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Staged Continual Adaptation of Multimodal Foundation Models for Japanese Financial Documents</title>
      <link>https://atsushiyanaigsawa768.github.io/mysite/en/blog/compass/</link>
      <pubDate>Wed, 13 May 2026 00:00:00 +0000</pubDate>
      <guid>https://atsushiyanaigsawa768.github.io/mysite/en/blog/compass/</guid>
      <description>Accepted at the CATS Workshop @ ICML 2026. We track an 8.4B-parameter multimodal model from an un-fine-tuned baseline (Phase 0) through three training phases on Japanese financial disclosures, and find that each benchmark peaks at a different phase — so the best checkpoint is task-dependent. This is the latest version of the Compass project; an earlier write-up targeting the FT-LLM 2026 competition is preserved as a legacy post.</description>
    </item>
  </channel>
</rss>
