<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>RSS 在投 on 北京大学智能科学与技术实验班</title><link>https://zhi-class.ai/zh-cn/tags/rss-%E5%9C%A8%E6%8A%95/</link><description>Recent content in RSS 在投 on 北京大学智能科学与技术实验班</description><generator>Hugo -- gohugo.io</generator><language>zh-CN</language><copyright>Copyright © Zhi Class 2022-2026</copyright><lastBuildDate>Thu, 12 Feb 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://zhi-class.ai/zh-cn/tags/rss-%E5%9C%A8%E6%8A%95/index.xml" rel="self" type="application/rss+xml"/><item><title>LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion</title><link>https://zhi-class.ai/zh-cn/research/2602.lda-1b/</link><pubDate>Thu, 12 Feb 2026 00:00:00 +0000</pubDate><guid>https://zhi-class.ai/zh-cn/research/2602.lda-1b/</guid><description>Recent robot foundation models largely rely on large-scale behavior cloning, which imitates expert actions but discards transferable dynamics knowledge embedded in heterogeneous embodied data.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://zhi-class.ai/zh-cn/research/2602.lda-1b/featured.zh-cn.jpg"/></item></channel></rss>