<?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>Benchmark on Xu'Blog</title><link>https://xuquant.com/tags/benchmark/</link><description>Recent content in Benchmark on Xu'Blog</description><image><title>Xu'Blog</title><url>https://xuquant.com/og-default.png</url><link>https://xuquant.com/og-default.png</link></image><generator>Hugo -- 0.152.2</generator><language>zh</language><lastBuildDate>Sun, 24 May 2026 11:00:00 +0800</lastBuildDate><atom:link href="https://xuquant.com/tags/benchmark/index.xml" rel="self" type="application/rss+xml"/><item><title>Affordance vs Symbolic Perception in AD：二分 framing 错在哪</title><link>https://xuquant.com/posts/autonomous-driving/affordance-vs-symbolic-perception/</link><pubDate>Sun, 24 May 2026 11:00:00 +0800</pubDate><guid>https://xuquant.com/posts/autonomous-driving/affordance-vs-symbolic-perception/</guid><description>AD 圈把 affordance / symbolic 当二分讨论，但 symbolic 一词同时指结构化感知输出和 language 输出，benchmark 排序不一致，Wayve / Tesla / 蔚小理实际站位都是 hybrid——这条 spectrum 是 framing 错位。真正决定 production VLA 的是几条独立工程 axis。</description></item></channel></rss>