<rss xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
  <channel>
    <title>(&#39;&#39;, &#39;cs.LGcs.AI&#39;) - Tag - leoleils-blog</title>
    <link>https://leoleils.top/tags/cs.lgcs.ai/</link>
    <description>(&#39;&#39;, &#39;cs.LGcs.AI&#39;) - Tag - leoleils-blog</description>
    <generator>Hugo -- gohugo.io</generator><language>zh-cn</language><lastBuildDate>Wed, 08 Apr 2026 12:00:00 &#43;0800</lastBuildDate><atom:link href="https://leoleils.top/tags/cs.lgcs.ai/" rel="self" type="application/rss+xml" /><item>
  <title>📄 In-Place Test-Time Training</title>
  <link>https://leoleils.top/posts/ai-paper/paper-2026-04-08-in-place-test-time-training/</link>
  <pubDate>Wed, 08 Apr 2026 12:00:00 &#43;0800</pubDate>
  <author>Author</author>
  <guid>https://leoleils.top/posts/ai-paper/paper-2026-04-08-in-place-test-time-training/</guid>
  <description><![CDATA[📖 论文基本信息 项目 内容 标题 In-Place Test-Time Training 作者 Guhao Feng, Shengjie Luo, Kai Hua, Ge Zhang, Di He&hellip; 机构 待补充 发布时间 2026-04-07 arXiv 编号 2604.06169v1 PDF 下载 点击下载 💡 一句话总结 The static ``train then deploy&quot; paradigm fundamentally limits Large Language Models (LLMs) from dynamically adapting their weights in response to continuous streams of new information inherent in real&hellip;
🎯 研究背景 这部分需要深入分析论文要解决的核心问题
现有挑战 待补充：现有方法的局限性 研究动机 待补充：为什么这个问题重要 🔬 核心创新 这部分需要提炼 3-5 个技术突破点]]></description>
</item>
<item>
  <title>📄 Enhancing Robustness of Federated Learning via Server Learni</title>
  <link>https://leoleils.top/posts/ai-paper/paper-2026-04-06-enhancing-robustness-of-federated-learning-via-ser/</link>
  <pubDate>Mon, 06 Apr 2026 12:00:00 &#43;0800</pubDate>
  <author>Author</author>
  <guid>https://leoleils.top/posts/ai-paper/paper-2026-04-06-enhancing-robustness-of-federated-learning-via-ser/</guid>
  <description><![CDATA[📖 论文基本信息 项目 内容 标题 Enhancing Robustness of Federated Learning via Server Learning 作者 Van Sy Mai, Kushal Chakrabarti, Richard J. La, Dipankar Maity 机构 待补充 发布时间 2026-04-03 arXiv 编号 2604.03226v1 PDF 下载 点击下载 💡 一句话总结 This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients&rsquo; training data are not independent and identically distrib&hellip;
🎯 研究背景 这部分需要深入分析论文要解决的核心问题
现有挑战 待补充：现有方法的局限性 研究动机 待补充：为什么这个问题重要 🔬 核心创新 这部分需要提炼 3-5 个技术突破点]]></description>
</item>
</channel>
</rss>
