<?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>Nvidia on Xu'Blog</title><link>https://xuquant.com/zh/tags/nvidia/</link><description>Recent content in Nvidia on Xu'Blog</description><image><title>Xu'Blog</title><url>https://xuquant.com/images/profile.jpg</url><link>https://xuquant.com/images/profile.jpg</link></image><generator>Hugo -- 0.152.2</generator><language>zh</language><lastBuildDate>Sun, 11 Jan 2026 10:00:00 +0800</lastBuildDate><atom:link href="https://xuquant.com/zh/tags/nvidia/index.xml" rel="self" type="application/rss+xml"/><item><title>Vision-Language-Action Models for Autonomous Driving: The Cosmos-Reason Approach</title><link>https://xuquant.com/zh/posts/autodrive/nvidia_vla/</link><pubDate>Sun, 11 Jan 2026 10:00:00 +0800</pubDate><guid>https://xuquant.com/zh/posts/autodrive/nvidia_vla/</guid><description>深入技术解析 Nvidia Cosmos-Reason (Alpamayo) VLA 自动驾驶系统，涵盖三平面视觉编码、自车捷径规避、变化因数据集范式，以及通过强化学习实现的推理-动作对齐。</description></item></channel></rss>