<?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>Ablation-Study on Xu'Blog</title><link>https://xuquant.com/tags/ablation-study/</link><description>Recent content in Ablation-Study 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>Thu, 28 May 2026 20:00:00 +0800</lastBuildDate><atom:link href="https://xuquant.com/tags/ablation-study/index.xml" rel="self" type="application/rss+xml"/><item><title>VLA 加几何 backbone 的负结果：GR00T × VGGT 三架构对照</title><link>https://xuquant.com/posts/foundation-models/vla-geometric-fusion-three-architectures/</link><pubDate>Thu, 28 May 2026 20:00:00 +0800</pubDate><guid>https://xuquant.com/posts/foundation-models/vla-geometric-fusion-three-architectures/</guid><description>NVIDIA + MIT + UT Austin 团队（arXiv:2605.24642）把 GR00T-N1.5 (manipulation VLA) 跟 VGGT (geometric foundation model) 拼起来，做了 Early Fusion / Late Fusion / Spatial Forcing 三种几何注入架构的 controlled 对照。主结果是一个负结果——standard finetune 下三种几何 VLA 都不显著超过 GR00T baseline。但 ablation 链里的几条判断（don&amp;#39;t unfreeze LLM、probe 改进不等于 task 改进、mid-training 比架构选择影响更大、gate 近零起步）跟 production AD VLA 的工程决策直接相关。</description></item></channel></rss>