<?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>空间智能 on gulucaptain's Blog</title><link>https://gulucaptain.github.io/DailyPaper/tags/%E7%A9%BA%E9%97%B4%E6%99%BA%E8%83%BD/</link><description>Recent content in 空间智能 on gulucaptain's Blog</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Sat, 05 Sep 2026 09:00:00 +0800</lastBuildDate><atom:link href="https://gulucaptain.github.io/DailyPaper/tags/%E7%A9%BA%E9%97%B4%E6%99%BA%E8%83%BD/index.xml" rel="self" type="application/rss+xml"/><item><title>Fei-Fei Li：世界模型将如何颠覆机器人与 3D？（a16z 访谈 World Labs 团队）</title><link>https://gulucaptain.github.io/DailyPaper/clips/a16z-fei-fei-li-world-models/</link><pubDate>Sat, 05 Sep 2026 09:00:00 +0800</pubDate><guid>https://gulucaptain.github.io/DailyPaper/clips/a16z-fei-fei-li-world-models/</guid><description>World Labs 三人组把 Atlas 的核心原语定义为 new view prediction（新视角预测），并宣称它与 next-token prediction 等价、同属 AI-complete——用相机位姿作为模型原生输入统一了此前分裂的像素生成与 3D 重建两条赛道，把稀疏重建…</description></item><item><title>李飞飞发布全球首个多模态世界模型 Atlas：像素级相机控制+单图生成完整 3D 世界</title><link>https://gulucaptain.github.io/DailyPaper/clips/world-labs-atlas/</link><pubDate>Thu, 03 Sep 2026 09:00:00 +0800</pubDate><guid>https://gulucaptain.github.io/DailyPaper/clips/world-labs-atlas/</guid><description>把相机位姿做成原生输入的全能世界模型，单图生成可自由探索的 3D 世界并直出点云与 3DGS</description></item></channel></rss>