<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>ICLR on PKU ZhiClass</title><link>https://zhi-class.ai/tags/iclr/</link><description>Recent content in ICLR on PKU ZhiClass</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>Copyright © Zhi Class 2022-2026</copyright><lastBuildDate>Mon, 26 Jan 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://zhi-class.ai/tags/iclr/index.xml" rel="self" type="application/rss+xml"/><item><title>Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields</title><link>https://zhi-class.ai/research/2601.learning-physics-grounded-4d-dynamics-with-neura/</link><pubDate>Mon, 26 Jan 2026 00:00:00 +0000</pubDate><guid>https://zhi-class.ai/research/2601.learning-physics-grounded-4d-dynamics-with-neura/</guid><description>Predicting physical dynamics from visual data remains a fundamental challenge in AI, as it requires both accurate scene understanding and robust physics reasoning.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://zhi-class.ai/research/2601.learning-physics-grounded-4d-dynamics-with-neura/featured.jpg"/></item><item><title>Neural Force Field: Few shot learning of generalized physical reasoning</title><link>https://zhi-class.ai/research/2601.neural-force-field/</link><pubDate>Mon, 26 Jan 2026 00:00:00 +0000</pubDate><guid>https://zhi-class.ai/research/2601.neural-force-field/</guid><description>We present NFF, a modeling framework built on NODE that learns interpretable force field representations which can be efficiently integrated through an ODE solver to predict object trajectories.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://zhi-class.ai/research/2601.neural-force-field/featured.jpg"/></item></channel></rss>