<?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>Grounding on Xu'Blog</title><link>https://xuquant.com/tags/grounding/</link><description>Recent content in Grounding 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>Mon, 27 Oct 2025 22:00:00 +0800</lastBuildDate><atom:link href="https://xuquant.com/tags/grounding/index.xml" rel="self" type="application/rss+xml"/><item><title>ReconVLA：用 gaze-crop 重建给 VLA 视觉接地</title><link>https://xuquant.com/posts/foundation-models/reconvla-gaze-crop-implicit-grounding/</link><pubDate>Mon, 27 Oct 2025 22:00:00 +0800</pubDate><guid>https://xuquant.com/posts/foundation-models/reconvla-gaze-crop-implicit-grounding/</guid><description>OpenHelix 的 ReconVLA (arXiv:2508.10333) 在 OpenVLA 风格的 backbone 后挂一个 3 层 DiT，用 gaze-crop 的 VAE-latent 重建当辅助监督，把 VLA 的注意力锚到目标物体上。本文对照 paper 与开源 code 读一遍，包含 paper 没强调的工程细节，以及几个 paper 没回答的问题——recon-on/off ablation 缺位，&amp;#39;隐式接地&amp;#39; 在训练 supervision 上其实依赖 offline YOLO bbox。</description></item></channel></rss>