<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Vision on Xiaolan Xu</title><link>https://xiaolan.in/tags/vision/</link><description>Recent content in Vision on Xiaolan Xu</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 04 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://xiaolan.in/tags/vision/index.xml" rel="self" type="application/rss+xml"/><item><title>The Question After the Demo</title><link>https://xiaolan.in/blog/the-question-after-the-demo/</link><pubDate>Sat, 04 Jul 2026 00:00:00 +0000</pubDate><guid>https://xiaolan.in/blog/the-question-after-the-demo/</guid><description>On April 24th I gave a demo of an AI-assisted, cloud-native pipeline for the SMAP-NISAR soil moisture algorithm — the kind of talk meant to show a platform working, not to make an argument. It landed well. People were generous about it afterward, including some fairly senior people at NASA HQ.
The interesting part happened after, in the informal Q&amp;amp;A. A colleague who works in formal verification — proving software and system contracts correct, not remote sensing — asked a question that had nothing to do with the pipeline I&amp;rsquo;d just shown.</description></item></channel></rss>