<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Multimodal Learning |</title><link>https://lelain.net/tags/multimodal-learning/</link><atom:link href="https://lelain.net/tags/multimodal-learning/index.xml" rel="self" type="application/rss+xml"/><description>Multimodal Learning</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 26 Oct 2026 00:00:00 +0000</lastBuildDate><image><url>https://lelain.net/media/icon.svg</url><title>Multimodal Learning</title><link>https://lelain.net/tags/multimodal-learning/</link></image><item><title>The Great Chat in the Sky: Aligning Exotic Astronomical Data to Language with AstroBridge</title><link>https://lelain.net/publications/astrobridge/</link><pubDate>Mon, 26 Oct 2026 00:00:00 +0000</pubDate><guid>https://lelain.net/publications/astrobridge/</guid><description>&lt;p&gt;Accepted at the Machine Learning and the Physical Sciences (ML4PS) 2026 workshop, co-located with NeurIPS 2026 and held at the Georgia Institute of Technology, Atlanta, on December 11, 2026.&lt;/p&gt;
&lt;p&gt;A
collaboration, following
. Where AstroLLaVA worked on outreach-style images, AstroBridge aligns raw scientific observations (images, spectra and light curves) with a language model, using captions generated from the literature that describes the same objects.&lt;/p&gt;</description></item></channel></rss>