<?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>Vision-Language Model on Po-Wei Chen, MD — Physiatrist &amp; Builder</title><link>https://drpwchen.com/en/tags/vision-language-model/</link><description>Recent content in Vision-Language Model on Po-Wei Chen, MD — Physiatrist &amp; Builder</description><image><title>Po-Wei Chen, MD — Physiatrist &amp; Builder</title><url>https://drpwchen.com/og-default.png</url><link>https://drpwchen.com/og-default.png</link></image><generator>Hugo</generator><language>en</language><lastBuildDate>Mon, 03 Aug 2026 14:30:00 +0800</lastBuildDate><atom:link href="https://drpwchen.com/en/tags/vision-language-model/index.xml" rel="self" type="application/rss+xml"/><item><title>Turning lecture videos into notes you'll actually revisit: lecture-to-notes is now open source</title><link>https://drpwchen.com/en/posts/lecture-to-notes/</link><pubDate>Mon, 03 Aug 2026 06:45:00 +0800</pubDate><guid>https://drpwchen.com/en/posts/lecture-to-notes/</guid><description>PM&amp;amp;R lectures hide their knowledge in movements. Everyone records them, but nobody goes back to finish watching them. lecture-to-notes turns recordings into three forms of notes: a video, a transcript, and a summary synced on a single webpage, plus markdown for Obsidian and a PDF. Transcription, OCR, and slide analysis all run on your local GPU. Open source under MIT.</description></item></channel></rss>