<?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>Gpt4-Generated on CharmingGroot</title>
    <link>https://charminggroot.github.io/tags/gpt4-generated/</link>
    <description>Recent content in Gpt4-Generated on CharmingGroot</description>
    <generator>Hugo</generator>
    <language>ko-kr</language>
    <lastBuildDate>Sun, 14 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://charminggroot.github.io/tags/gpt4-generated/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>094. LLaVA — 오픈소스 멀티모달 LLM</title>
      <link>https://charminggroot.github.io/posts/094-llava/</link>
      <pubDate>Sun, 14 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://charminggroot.github.io/posts/094-llava/</guid>
      <description>LLaVA(2023)는 CLIP 비전 인코더와 LLaMA를 선형 투영 레이어 하나로 연결한 오픈소스 멀티모달 모델이다. GPT-4가 생성한 158K 시각 지시 데이터로 학습해 GPT-4V에 가까운 시각 추론 능력을 보인다.</description>
    </item>
  </channel>
</rss>
