<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hu Jiawei 胡家伟 | Trustworthy AI Systems Lab (TAS Lab)</title><link>https://tas-lab.org/author/jiawei-hu/</link><atom:link href="https://tas-lab.org/author/jiawei-hu/index.xml" rel="self" type="application/rss+xml"/><description>Hu Jiawei 胡家伟</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><image><url>https://tas-lab.org/author/jiawei-hu/avatar_hu_42ed58fde12e8f21.jpg</url><title>Hu Jiawei 胡家伟</title><link>https://tas-lab.org/author/jiawei-hu/</link></image><item><title>Hu Jiawei 胡家伟</title><link>https://tas-lab.org/author/jiawei-hu/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://tas-lab.org/author/jiawei-hu/</guid><description>&lt;p&gt;Jiawei Hu is a graduate student at the SHEIN-MING WU School of Intelligent Engineering, South China University of Technology. He recently completed his bachelor's degree and is now pursuing further research in large language model safety, with a focus on system prompt robustness and jailbreak attack defense.&lt;/p&gt;</description></item></channel></rss>