<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Machine Learning | Uzziel Perez</title><link>https://www.uzzielperez.com/tags/machine-learning/</link><atom:link href="https://www.uzzielperez.com/tags/machine-learning/index.xml" rel="self" type="application/rss+xml"/><description>Machine Learning</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Fri, 29 May 2026 00:00:00 +0000</lastBuildDate><image><url>https://www.uzzielperez.com/media/icon_hu7729264130191091259.png</url><title>Machine Learning</title><link>https://www.uzzielperez.com/tags/machine-learning/</link></image><item><title>Three talks at CHEP 2026 in Bangkok</title><link>https://www.uzzielperez.com/post/chep2026-three-talks/</link><pubDate>Fri, 29 May 2026 00:00:00 +0000</pubDate><guid>https://www.uzzielperez.com/post/chep2026-three-talks/</guid><description>&lt;p>I presented three talks at &lt;a href="https://indico.cern.ch/" target="_blank" rel="noopener">CHEP 2026&lt;/a>, the 28th International Conference on Computing in High Energy and Nuclear Physics, hosted by Chulalongkorn University in Bangkok, Thailand (May 25–29, 2026):&lt;/p>
&lt;ol>
&lt;li>&lt;strong>When Less is More&lt;/strong> — lightweight and distilled graph neural networks for efficient particle reconstruction in LHCb&amp;rsquo;s next-generation PicoCal calorimeter.&lt;/li>
&lt;li>&lt;strong>Optimizing GNNs for the Wild&lt;/strong> — PyTorch-to-ONNX acceleration of GarNet on CPUs and GPUs, targeting the LHCb GPU trigger.&lt;/li>
&lt;li>&lt;strong>Future-Ready Restoration&lt;/strong> — a case study on RAG-enhanced, agentic revival of a Run-2 Λb → Λγ analysis.&lt;/li>
&lt;/ol>
&lt;p>Details for each talk are on the &lt;a href="https://www.uzzielperez.com/event/">talks page&lt;/a>.&lt;/p></description></item></channel></rss>