<?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>World Models on Aaron Appelle</title><link>https://aaronappelle.github.io/tags/world-models/</link><description>Recent content in World Models on Aaron Appelle</description><generator>Hugo -- 0.147.2</generator><language>en</language><lastBuildDate>Thu, 23 Oct 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://aaronappelle.github.io/tags/world-models/index.xml" rel="self" type="application/rss+xml"/><item><title>Evaluating Video Models as Simulators of Multi-Person Pedestrian Trajectories</title><link>https://aaronappelle.github.io/research/video_ped/</link><pubDate>Thu, 23 Oct 2025 00:00:00 +0000</pubDate><guid>https://aaronappelle.github.io/research/video_ped/</guid><description>This paper proposes a rigorous evaluation protocol to benchmark text-to-video and image-to-video models as implicit simulators of pedestrian dynamics. Preprint, under review.</description></item><item><title>Can Image-To-Video Models Simulate Pedestrian Dynamics?</title><link>https://aaronappelle.github.io/research/icml_wm/</link><pubDate>Sat, 19 Jul 2025 00:00:00 +0000</pubDate><guid>https://aaronappelle.github.io/research/icml_wm/</guid><description>This paper investigates whether image-to-video models can generate realistic pedestrian movement patterns in crowded public scenes. Presented at ICML 2025 Workshop on Building Physically Plausible World Models.</description></item></channel></rss>