<?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>LLM on Bluue Whale</title><link>https://bluuewhale.github.io/tags/llm/</link><description>Recent content in LLM on Bluue Whale</description><image><title>Bluue Whale</title><url>https://bluuewhale.github.io/images/profile.jpg</url><link>https://bluuewhale.github.io/images/profile.jpg</link></image><generator>Hugo -- 0.152.2</generator><language>en-us</language><lastBuildDate>Sat, 22 Aug 2026 22:21:36 +0900</lastBuildDate><atom:link href="https://bluuewhale.github.io/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>LightMem: Lightweight and Efficient Memory-Augmented Generation</title><link>https://bluuewhale.github.io/posts/lightmem-en/</link><pubDate>Mon, 06 Apr 2026 14:12:30 +0900</pubDate><guid>https://bluuewhale.github.io/posts/lightmem-en/</guid><description>How LightMem cuts token waste in LLM memory systems with a three-tier structure modeled on the Atkinson-Shiffrin memory model: sensory memory, topic-aware short-term memory, and long-term memory.</description></item><item><title>GraphRAG</title><link>https://bluuewhale.github.io/posts/graphrag-en/</link><pubDate>Fri, 13 Mar 2026 10:26:08 +0900</pubDate><guid>https://bluuewhale.github.io/posts/graphrag-en/</guid><description>How GraphRAG combines knowledge graphs with community detection to answer questions that need a view of an entire corpus, walked through its indexing/query pipeline and evaluation results.</description></item></channel></rss>