<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/b51b5e3ce227442d9d9ca2a00bd9d03c&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/b51b5e3ce227442d9d9ca2a00bd9d03c-00001.gif</thumbnail_url><duration>280.554</duration><title>Latent Lab Demo</title><description>Hi, I&apos;m Trudy. In this video, I&apos;ll be giving you a quick demo of Layton Lab, a project I worked on at the MIT Media Lab with Kevin Dennell and Andrew Stoddard. Layton Lab is a visually appealing knowledge base exploration tool powered by an LLM (Large Language Model). I&apos;ll show you how we use embeddings to create a similarity map of research projects and how you can generate project summaries and even create new research projects based on past ones. Watch the video to learn more!</description></oembed>