<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Refrag on Neat Guy Coding</title><link>https://neatguycoding.com/tags/refrag/</link><description>Recent content in Refrag on Neat Guy Coding</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2026 NeatGuyCoding</copyright><lastBuildDate>Mon, 18 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://neatguycoding.com/tags/refrag/index.xml" rel="self" type="application/rss+xml"/><item><title>REFRAG: Turning RAG Context from a Token String into a Compressible Representation</title><link>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-refrag-with-xiaoqiang-lin-weaviate-podcast-130/</link><pubDate>Mon, 18 May 2026 00:00:00 +0000</pubDate><guid>https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-refrag-with-xiaoqiang-lin-weaviate-podcast-130/</guid><description>REFRAG compresses retrieved passages into chunk-level decoder positions, then uses RL to selectively expand high-entropy spans—mechanisms, training pipeline, and how to read TTFT and RAG benchmarks without over-generalizing paper numbers.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://neatguycoding.com/posts/2026-05-18-weaviate-podcast-refrag-with-xiaoqiang-lin-weaviate-podcast-130/cover.png"/></item></channel></rss>