<?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>Multimodal on axiom-ai.tech</title><link>https://axiom-ai.tech/tags/multimodal/</link><description>Recent content in Multimodal on axiom-ai.tech</description><image><title>axiom-ai.tech</title><url>https://axiom-ai.tech/og-image.png</url><link>https://axiom-ai.tech/og-image.png</link></image><generator>Hugo</generator><language>en-gb</language><copyright>2026 Anirban Datta</copyright><lastBuildDate>Sun, 27 Sep 2026 00:00:00 +0530</lastBuildDate><atom:link href="https://axiom-ai.tech/tags/multimodal/index.xml" rel="self" type="application/rss+xml"/><item><title>What Happens When Computers Look at Pictures?</title><link>https://axiom-ai.tech/generative-ai/vision/01-prologue/</link><pubDate>Sun, 27 Sep 2026 00:00:00 +0530</pubDate><guid>https://axiom-ai.tech/generative-ai/vision/01-prologue/</guid><description>From a grid of numbers to a sentence that understands it: the beginning of a series on how AI learns to see.</description></item></channel></rss>