From Masks to Worlds: A Hitchhiker’s Guide to World Models

Jinbin Bai, Yu Lei, Hecong Wu, Yuchen Zhu, Zhuoran Zhao

Keywords: World Models, Position Paper

Abstract: This is not a typical survey of world models, it is a guide for those who want to build worlds. We do not aim to catalog every paper that has ever mentioned a ``world model". Instead, we follow one clear road: from early masked models that unified representation learning across modalities, to unified architectures that share a single paradigm, then to interactive generative models that close the action-perception loop, and finally to memory-augmented systems that sustain consistent worlds over time. We bypass noisy branches to focus on the core: the generative heart, the interactive loop, and the memory system. We show that this is the most promising path towards world models.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 2999