<?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>Vision-Language-Action on Sankalp&#39;s Blog</title>
    <link>https://sankalpshekhar.com/tags/vision-language-action/</link>
    <description>Recent content in Vision-Language-Action on Sankalp&#39;s Blog</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Wed, 29 Jul 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://sankalpshekhar.com/tags/vision-language-action/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>VLA Models: Why Hardware Is Harder Than Text</title>
      <link>https://sankalpshekhar.com/posts/vla-models-hardware-is-hard/</link>
      <pubDate>Wed, 29 Jul 2026 00:00:00 +0000</pubDate>
      <guid>https://sankalpshekhar.com/posts/vla-models-hardware-is-hard/</guid>
      <description>I spent a few weeks reading VLA papers thinking they&amp;#39;d be LLMs with a robot head. Turns out, 200 ms of latency isn&amp;#39;t a UI glitch when there&amp;#39;s a physical arm involved.</description>
    </item>
  </channel>
</rss>
