<?xml version='1.0' encoding='UTF-8'?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Physical Intelligence Blog</title>
    <link>https://www.pi.website/</link>
    <description>Latest blog posts and research from Physical Intelligence</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>RSS Creator</generator>
    <language>zh-CN</language>
    <lastBuildDate>Thu, 24 Sep 2026 01:12:07 +0000</lastBuildDate>
    <item>
      <title>π0.7: a Steerable Model with Emergent Capabilities</title>
      <link>https://www.pi.website/blog/pi07</link>
      <description>A steerable robotic foundation model that exhibits a step-change in generalization.</description>
      <guid isPermaLink="true">https://www.pi.website/blog/pi07</guid>
      <pubDate>Thu, 16 Apr 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>The Physical Intelligence Layer</title>
      <link>https://www.pi.website/blog/partner</link>
      <description>General-purpose physical intelligence models will enable a Cambrian explosion of robotics applications. See how our partners are already solving real-world problems.</description>
      <guid isPermaLink="true">https://www.pi.website/blog/partner</guid>
      <pubDate>Tue, 24 Feb 2026 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Moravec's Paradox and the Robot Olympics</title>
      <link>https://www.pi.website/blog/olympics</link>
      <description>By fine-tuning our latest model, we were able to solve a series of very difficult manipulation challenge tasks.</description>
      <guid isPermaLink="true">https://www.pi.website/blog/olympics</guid>
      <pubDate>Mon, 22 Dec 2025 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>π0.6*: a VLA that Learns from Experience</title>
      <link>https://www.pi.website/blog/pistar06</link>
      <description>A method for training our generalist policies with RL to improve success rate and throughput on real-world tasks.</description>
      <guid isPermaLink="true">https://www.pi.website/blog/pistar06</guid>
      <pubDate>Mon, 17 Nov 2025 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>π0.5: a VLA with Open-World Generalization</title>
      <link>https://www.pi.website/blog/pi05</link>
      <description>Our latest generalist policy, π0.5, extends π0 and enables open-world generalization. Our new model can control a mobile manipulator to clean up an entirely new kitchen or bedroom.</description>
      <guid isPermaLink="true">https://www.pi.website/blog/pi05</guid>
      <pubDate>Tue, 22 Apr 2025 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>Open Sourcing π0</title>
      <link>https://www.pi.website/blog/openpi</link>
      <description>We are releasing the weights and code for π0 as well as our new π0-FAST autoregressive model.</description>
      <guid isPermaLink="true">https://www.pi.website/blog/openpi</guid>
      <pubDate>Tue, 04 Feb 2025 00:00:00 +0000</pubDate>
    </item>
    <item>
      <title>π0: Our First Generalist Policy</title>
      <link>https://www.pi.website/blog/pi0</link>
      <description>Our first generalist policy, π0, a prototype model that combines large-scale multi-task and multi-robot data collection with a new network architecture to enable the most capable and dexterous generalist robot policy to date.</description>
      <guid isPermaLink="true">https://www.pi.website/blog/pi0</guid>
      <pubDate>Thu, 31 Oct 2024 00:00:00 +0000</pubDate>
    </item>
  </channel>
</rss>
