<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Training-Free Learning | The personal website of Shuai Zhang</title><link>https://www.shuaizhang-hkust.cn/tags/training-free-learning/</link><atom:link href="https://www.shuaizhang-hkust.cn/tags/training-free-learning/index.xml" rel="self" type="application/rss+xml"/><description>Training-Free Learning</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 17 Sep 2026 00:00:00 +0000</lastBuildDate><image><url>https://www.shuaizhang-hkust.cn/media/icon_hu_1e527f1804e84236.png</url><title>Training-Free Learning</title><link>https://www.shuaizhang-hkust.cn/tags/training-free-learning/</link></image><item><title>CitySTAR: Agent-Driven Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding</title><link>https://www.shuaizhang-hkust.cn/publications/conference-paper/citystar-neurips-2026/</link><pubDate>Thu, 17 Sep 2026 00:00:00 +0000</pubDate><guid>https://www.shuaizhang-hkust.cn/publications/conference-paper/citystar-neurips-2026/</guid><description>&lt;p&gt;CitySTAR was accepted at &lt;strong&gt;NeurIPS 2026&lt;/strong&gt;. The linked arXiv version uses the
earlier title “CitySTAR: Structured and Topology-Aware Reasoning for
Open-Vocabulary Urban 3D Grounding”.&lt;/p&gt;</description></item><item><title>GeoOpen3D: Geometry-guided training-free open-vocabulary 3D segmentation via visual foundation models</title><link>https://www.shuaizhang-hkust.cn/publications/conference-paper/geoopen3d-isprs-2026/</link><pubDate>Thu, 23 Jul 2026 00:00:00 +0000</pubDate><guid>https://www.shuaizhang-hkust.cn/publications/conference-paper/geoopen3d-isprs-2026/</guid><description/></item></channel></rss>