World-In-World: World Models in a Closed-Loop World

ICLROral2026

Authors: Jiahan Zhang, Muqing Jiang, Nanru Dai, TaiMing Lu, Arda Uzunoglu, Shunchi Zhang, Yana Wei, Jiahao Wang, Vishal M. Patel, Paul Pu Liang, Daniel Khashabi, Cheng Peng, Rama Chellappa, Tianmin Shu, Alan Yuille, Yilun Du, Jieneng Chen
Venue: ICLR 2026
Track: Oral

TL;DR

By grounding assessment in embodied task success instead of video metrics, World-In-World provides a principled yardstick for future research on generative world models in the context of embodiment…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

world model video

← All ICLR 2026 Oral papers · Browse the whole archive