English

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

Machine Learning 2025-10-24 v1

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 loosely related 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 true world models.

Keywords

Cite

@article{arxiv.2510.20668,
  title  = {From Masks to Worlds: A Hitchhiker's Guide to World Models},
  author = {Jinbin Bai and Yu Lei and Hecong Wu and Yuchen Zhu and Shufan Li and Yi Xin and Xiangtai Li and Molei Tao and Aditya Grover and Ming-Hsuan Yang},
  journal= {arXiv preprint arXiv:2510.20668},
  year   = {2025}
}

Comments

Github: https://github.com/M-E-AGI-Lab/Awesome-World-Models