提出世界模型的上下文学习机制，揭示动态适应的关键条件。
Context and Diversity Matter: The Emergence of In-Context Learning in World Models
- 定义环境识别与环境学习两大机制，解释上下文学习如何形成。
- 推导误差上界，证明长上下文和多样化环境是关键前提。
- 实验证实机制存在，且模型架构与数据分布影响学习效果。
预测环境动态是生物神经网络与通用具身智能体适应环境的核心能力。然而，现有方法依赖静态世界模型，在面对新奇或罕见配置时表现不佳。本文研究世界模型的上下文学习（ICL），关注模型能力的增长与极限，而非零样本性能。贡献有三：(1) 形式化世界模型的ICL，识别出两个核心机制——环境识别（ER）与环境学习（EL）；(2) 推导两者误差上界，揭示机制出现的条件；(3) 实验验证不同ICL机制的存在，并系统研究数据分布与模型架构对ICL的影响，结果与理论一致。研究展示出自适应世界模型的潜力，强调长上下文与多样化环境在EL/ER涌现中的决定性作用。
原文摘要 · Abstract (English)
The capability of predicting environmental dynamics underpins both biological neural systems and general embodied AI in adapting to their surroundings. Yet prevailing approaches rest on static world models that falter when confronted with novel or rare configurations. We investigate in-context learning (ICL) of world models, shifting attention from zero-shot performance to the growth and asymptotic limits of the world model. Our contributions are three-fold: (1) we formalize ICL of a world model and identify two core mechanisms: environment recognition (ER) and environment learning (EL); (2) we derive error upper-bounds for both mechanisms that expose how the mechanisms emerge; and (3) we empirically confirm that distinct ICL mechanisms exist in the world model, and we further investigate how data distribution and model architecture affect ICL in a manner consistent with theory. These findings demonstrate the potential of self-adapting world models and highlight the key factors behind the emergence of EL/ER, most notably the necessity of long context and diverse environments.
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。