从掩码到世界：世界模型的漫游指南

摘要

本文并非传统意义上的世界模型综述，而是面向构建者的实践指南。我们无意罗列所有提及"世界模型"的文献，而是沿着清晰脉络展开：从早期实现跨模态表征学习统一的掩码模型，到采用单一范式的融合架构，再到实现感知-行动闭环的交互式生成模型，最终抵达能够维持世界持续性的记忆增强系统。我们摒弃松散关联的技术分支，聚焦三大核心要素：生成引擎、交互闭环与记忆系统，论证这正是通往真正世界模型的最具前景的路径。

English

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.

从掩码到世界：世界模型的漫游指南

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

摘要

Support