让模型从观察中构建可执行的理论，像人一样理解世界运作机制。
Learning to Theorize the World from Observation
- 用可执行程序表示世界理论，支持组合式推理
- 在新场景中实现解释驱动的泛化能力
- 适合研究认知启发式学习与可解释AI
理解世界意味着什么？当前世界模型将理解等同于对潜在空间或观测空间的准确未来预测。但发展认知科学认为，人类理解源于在语言成熟前就构建内部理论。受此启发，我们提出「学习建理」范式，从原始非文本观察中推断显式的解释性理论。我们以神经理论家（NEO）实现该范式：一个概率神经模型，通过共享转移模型执行从观察中推导出的潜在程序，这些程序构成一种可学习的思维语言。在NEO中，理论表现为可执行、组合性的程序，其学习到的基元可系统重组以解释新现象。实验表明，该方法实现了基于解释的泛化，使观察能被其生成程序所理解。
原文摘要 · Abstract (English)
What does it mean to understand the world? Contemporary world models often operationalize understanding as accurate future prediction in latent or observation space. Developmental cognitive science, however, suggests a different view: human understanding emerges through the construction of internal theories of how the world works, even before mature language is acquired. Inspired by this theory-building view of cognition, we introduce Learning-to-Theorize, a learning paradigm for inferring explicit explanatory theories of the world from raw, non-textual observations. We instantiate this paradigm with the Neural Theorizer (NEO), a probabilistic neural model that induces latent programs as a learned Language of Thought and executes them through a shared transition model. In NEO, a theory is represented as an executable, compositional program whose learned primitives can be systematically recombined to explain novel phenomena. Experiments show that this formulation enables explanation-driven generalization, allowing observations to be understood in terms of the programs that generate them.
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。