从掩码模型到可交互世界，指引构建通用世界模型的四步路径。
From Masks to Worlds: A Hitchhiker's Guide to World Models
- 由多模态表征到统一架构，逐步构建可交互的世界模型
- 通过生成式建模与感知-行动闭环，实现动态世界演化
- 适合想构建长期一致、有记忆能力智能体的研究者
本文不是对世界模型的泛泛综述，而是为希望构建世界系统的研究者提供的实践指南。我们不罗列所有提及‘世界模型’的论文，而是沿着一条清晰脉络：从早期的多模态掩码模型，到共享统一范式的架构，再到闭合感知-行动回路的交互生成模型，最终发展到具备记忆增强的系统以维持长时间一致性。我们跳过松散关联的方向，聚焦核心：生成核心、交互回路与记忆系统。证明这是通往真正世界模型最具前景的路径。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。