<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>GUI Understanding | Yiqiao Jin CS PhD @ Georgia Tech</title><link>https://ahren09.github.io/tags/gui-understanding/</link><atom:link href="https://ahren09.github.io/tags/gui-understanding/index.xml" rel="self" type="application/rss+xml"/><description>GUI Understanding</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 30 Apr 2025 00:00:00 +0000</lastBuildDate><image><url>https://ahren09.github.io/media/icon_hu_eee6347cbdb2cc3f.png</url><title>GUI Understanding</title><link>https://ahren09.github.io/tags/gui-understanding/</link></image><item><title>ScreenLLM: Stateful Screen Schema for Efficient Action Understanding and Prediction</title><link>https://ahren09.github.io/publication/webconf25_screenllm/</link><pubDate>Wed, 30 Apr 2025 00:00:00 +0000</pubDate><guid>https://ahren09.github.io/publication/webconf25_screenllm/</guid><description>&lt;h2 id="abstract">Abstract&lt;/h2>
&lt;p>We introduce ScreenLLM, a specialized multimodal LLM for Graphical User Interface (GUI) understanding and action prediction. ScreenLLM proposes a stateful screen schema that represents dynamic user sessions as compact, time-aware textual summaries, and a high-efficiency key-frame extraction method based on second-order pixel changes to isolate significant UI transitions.&lt;/p>
&lt;h2 id="links">Links&lt;/h2>
&lt;ul>
&lt;li>
&lt;/li>
&lt;/ul></description></item></channel></rss>