<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>ICML-2026 on AI Science Report</title>
    <link>https://aiscience.uk/tags/icml-2026/</link>
    <description>Recent content in ICML-2026 on AI Science Report</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 26 Jun 2026 00:00:00 +0800</lastBuildDate>
    <atom:link href="https://aiscience.uk/tags/icml-2026/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AI Just Broke a 50-Year Bottleneck in Molecular Simulation — by Borrowing the Transformer</title>
      <link>https://aiscience.uk/posts/autoregressive-boltzmann-generators-arbg/</link>
      <pubDate>Fri, 26 Jun 2026 00:00:00 +0800</pubDate>
      <guid>https://aiscience.uk/posts/autoregressive-boltzmann-generators-arbg/</guid>
      <description>&lt;p&gt;1|In 2020, a team at MIT used reinforcement learning to discover halicin, a powerful new antibiotic hiding in plain sight among thousands of existing drugs. The AI found it in days. What most people missed was the bottleneck that makes that kind of discovery so rare: before you can search for new molecules, you need to understand how existing ones behave, and that means simulating them at the atomic level. That computational nightmare quietly strangles drug discovery, materials science, and every field that depends on molecular simulation.&#xA;2|&#xA;3|&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
