<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
	<channel>
		<title>Document Profiling on AIBussin — AI applications, systems and books</title>
		<link>https://aibussin.com/tags/document-profiling/</link>
		<description>Recent content in Document Profiling on AIBussin — AI applications, systems and books</description>
		<generator>Hugo</generator>
		<language>en-US</language>
		
		
		
		
			<lastBuildDate>Tue, 17 Jun 2025 23:31:13 +0100</lastBuildDate>
		
			<atom:link href="https://aibussin.com/tags/document-profiling/index.xml" rel="self" type="application/rss+xml" />
			<item>
				<title>Document Intelligence: Turning Documents into Structured Knowledge</title>
				<link>https://aibussin.com/post/docs/</link>
				<pubDate>Tue, 17 Jun 2025 23:31:13 +0100</pubDate>
				<guid>https://aibussin.com/post/docs/</guid>
				<description>&lt;h2 id=&#34;-summary&#34;&gt;📖 Summary&lt;/h2&gt;&#xA;&lt;p&gt;Imagine drowning in a sea of research papers, each holding a fragment of the knowledge you need for your next breakthrough. How does an AI system, striving for self-improvement, navigate this information overload to find precisely what it needs? This is the core challenge our Document Intelligence pipeline addresses, transforming chaotic documents into organized, searchable knowledge.&lt;/p&gt;&#xA;&lt;p&gt;In this post we combine insights from &lt;a href=&#34;https://arxiv.org/pdf/2505.21497&#34; target=&#34;_blank&#34; class=&#34;paper-badge&#34;&#xA;    style=&#34;display: inline-block; padding: 6px 10px; background: #f3f4f6; border-left: 4px solid #3b82f6; border-radius: 4px; margin: 4px 0; text-decoration: none; color: #1f2937;&#34;&gt;&#xA;    &lt;strong&gt;Paper2Poster&lt;/strong&gt;: Towards Multimodal Poster Automation from Scientific Papers&#xA;&lt;/a&gt; and&#xA;&lt;a href=&#34;https://arxiv.org/abs/2506.10952&#34; target=&#34;_blank&#34; class=&#34;paper-badge&#34;&#xA;    style=&#34;display: inline-block; padding: 6px 10px; background: #f3f4f6; border-left: 4px solid #3b82f6; border-radius: 4px; margin: 4px 0; text-decoration: none; color: #1f2937;&#34;&gt;&#xA;    &lt;strong&gt;Domain2Vec&lt;/strong&gt;: Vectorizing Datasets to Find the Optimal Data Mixture without Training&#xA;&lt;/a&gt; to build an AI document profiler that transforms unstructured papers into structured, searchable knowledge graphs.&lt;/p&gt;</description>
			</item>
	</channel>
</rss>
