<?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>Methodology on Xu'Blog</title><link>https://xuquant.com/tags/methodology/</link><description>Recent content in Methodology on Xu'Blog</description><image><title>Xu'Blog</title><url>https://xuquant.com/og-default.png</url><link>https://xuquant.com/og-default.png</link></image><generator>Hugo -- 0.152.2</generator><language>zh</language><lastBuildDate>Sat, 18 Apr 2026 18:00:00 +0800</lastBuildDate><atom:link href="https://xuquant.com/tags/methodology/index.xml" rel="self" type="application/rss+xml"/><item><title>凯明的方法论：从 ResNet 到 iMF —— 一个本质追问者的研究路径</title><link>https://xuquant.com/posts/foundation-models/kaiming-he-cvpr2026-five-papers-flow-matching-breakthrough/</link><pubDate>Sat, 18 Apr 2026 18:00:00 +0800</pubDate><guid>https://xuquant.com/posts/foundation-models/kaiming-he-cvpr2026-five-papers-flow-matching-breakthrough/</guid><description>以 iMF（Improved Mean Flow，arXiv:2512.02012）为主线深读何恺明 2026 CVPR 工作，并把它放回 ResNet / MoCo / MAE / SiT 十年脉络中，抓四条贯穿性的方法论 DNA：朴素到极致、改变问题假设、强先验少假设、方法与任务解耦。强链 mathematics/diffusion 系列。</description></item></channel></rss>