<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Long-Context on MdJawad</title><link>https://www.mdjawad.com/tags/long-context/</link><description>Recent content in Long-Context on MdJawad</description><generator>Hugo -- 0.148.2</generator><language>en-us</language><lastBuildDate>Sat, 23 May 2026 12:00:00 +0800</lastBuildDate><atom:link href="https://www.mdjawad.com/tags/long-context/index.xml" rel="self" type="application/rss+xml"/><item><title>Rotary Positional Encoding: Why Position Is a Rotation</title><link>https://www.mdjawad.com/posts/rotary-positional-encoding/</link><pubDate>Sat, 23 May 2026 12:00:00 +0800</pubDate><guid>https://www.mdjawad.com/posts/rotary-positional-encoding/</guid><description>An intuitive, visual guide to Rotary Positional Encoding. Why spinning the query and key vectors beats stamping a position number onto them, why a dot product only ever feels the angle between two vectors, and why that hands you relative position for free. The starting point for understanding how LLMs stretch to long context.</description></item></channel></rss>