世界模型通过预测一致性自发形成相似内部结构。
Platonic Representation Hypothesis on World Models
- 基于预测一致性假设，多模型在共享状态转移目标下趋同。
- 不同视觉编码器构建的模型内部结构几何相似度高。
- 模型间特征可映射，适合跨模型迁移与集成应用。
世界模型在感知与模拟复杂环境方面展现出巨大潜力，但其学习表征的本质仍不清楚。本文通过提出预测一致性假设，探究世界模型中的柏拉图表征假说：我们假设共享状态转移目标的优化过程会形成选择压力，促使异构模型收敛至共同的潜在结构。通过对DINO世界模型（DINO-WM）进行系统实验，改变视觉编码器以生成异构模型，发现具备能力的世界模型会演化出几何相似的内部结构。此外，通过模型拼接实验，证明一个世界模型的内部特征可映射到另一个模型，且性能损失有限，表明其功能兼容性。研究结果表明，追求预测一致性可促进世界模型间共享、可转换的潜在结构。
原文摘要 · Abstract (English)
World models have demonstrated significant potential for perceiving and simulating complex environments. Despite their strong performance, the fundamental nature of their learned representations remains poorly understood. In this paper, we investigate the Platonic Representation Hypothesis within this domain by proposing the Predictive Consistency Assumption: we posit that the optimization of a shared state transition objective acts as a selective pressure that encourages heterogeneous models to converge toward a shared latent structure. Through systematic experiments with the DINO World Model (DINO-WM), in which we vary visual encoders to create heterogeneous models, we find that capable world models evolve toward geometrically similar internal structures. Moreover, via model stitching, we show that the internal features of one world model can be mapped to another with limited performance degradation, providing evidence of functional compatibility. Our findings suggest that the pursuit of predictive consistency can promote shared, transition-compatible latent structure across 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。