<?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>MIT 6.5940 on 노란토끼의 기술 블로그</title><link>https://bias92.github.io/categories/mit-6.5940/</link><description>Recent content in MIT 6.5940 on 노란토끼의 기술 블로그</description><generator>Hugo -- 0.147.0</generator><language>ko</language><lastBuildDate>Sun, 15 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://bias92.github.io/categories/mit-6.5940/index.xml" rel="self" type="application/rss+xml"/><item><title>6.5940 L01 — Introduction and Overview</title><link>https://bias92.github.io/posts/6.5940-lec01-introduction/</link><pubDate>Sun, 15 Mar 2026 00:00:00 +0000</pubDate><guid>https://bias92.github.io/posts/6.5940-lec01-introduction/</guid><description>MIT 6.5940 (Song Han) Lecture 1 정리. DNN 효율화의 필요성부터 Model Compression, Quantization(AWQ/SmoothQuant/RTN), Sparsity, Edge AI, VLM/VILA, Hardware Trend까지.</description></item></channel></rss>