<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Mixture-of-Recursions &#8211; BIOENGINEER.ORG</title>
	<atom:link href="https://bioengineer.org/tag/mixture-of-recursions/feed/" rel="self" type="application/rss+xml" />
	<link>https://bioengineer.org</link>
	<description>Bioengineering</description>
	<lastBuildDate>Sun, 18 Oct 2026 13:14:29 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=7.1.3</generator>

<image>
	<url>https://bioengineer.org/wp-content/uploads/2019/09/cropped-bioengineering-32x32.png</url>
	<title>Mixture-of-Recursions &#8211; BIOENGINEER.ORG</title>
	<link>https://bioengineer.org</link>
	<width>32</width>
	<height>32</height>
</image> 
<site xmlns="com-wordpress:feed-additions:1">72741379</site>	<item>
		<title>AI Learns to Think Harder Only When Satellite Images Get Tricky</title>
		<link>https://bioengineer.org/ai-learns-to-think-harder-only-when-satellite-images-get-tricky/</link>
		
		<dc:creator><![CDATA[]]></dc:creator>
		<pubDate>Sun, 18 Oct 2026 13:14:29 +0000</pubDate>
				<category><![CDATA[Technology]]></category>
		<category><![CDATA[CLIP]]></category>
		<category><![CDATA[Computer Vision]]></category>
		<category><![CDATA[cross-attention]]></category>
		<category><![CDATA[deep learning]]></category>
		<category><![CDATA[LoRA]]></category>
		<category><![CDATA[Machine Learning]]></category>
		<category><![CDATA[Mixture-of-Recursions]]></category>
		<category><![CDATA[parameter-efficient fine-tuning]]></category>
		<category><![CDATA[remote sensing]]></category>
		<category><![CDATA[satellite imagery]]></category>
		<category><![CDATA[scene classification]]></category>
		<category><![CDATA[vision transformer]]></category>
		<guid isPermaLink="false">https://bioengineer.org/?p=434782</guid>

					<description><![CDATA[Researchers have unveiled MiRAGE, a parameter-efficient AI framework that adapts its computational depth to each satellite image and uses CLIP language embeddings to initialize its classifiers, ranking first among 92 methods across three remote sensing benchmarks.]]></description>
		
		
		
		<post-id xmlns="com-wordpress:feed-additions:1">434782</post-id>	</item>
	</channel>
</rss>
