发表机构
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对世界模型的表征性质，提出预测一致性假设，通过DINO-WM实验发现性能良好的世界模型会形成几何相似的内部结构，且模型特征可跨模型映射，证实预测一致性能促进共享潜在结构的形成。
AI 中文摘要
世界模型在感知和模拟复杂环境方面已展现出巨大潜力。尽管其性能强劲，但其学习到的表征的基本性质仍鲜为人知。在本文中，我们在该领域内研究柏拉图式表征假说，提出预测一致性假设：我们假设对共享状态转移目标的优化会产生选择压力，促使异构模型收敛至共享的潜在结构。通过对DINO世界模型（DINO-WM）开展系统实验，我们改变视觉编码器以构建异构模型，发现性能良好的世界模型会演化出几何上相似的内部结构。此外，通过模型拼接，我们证明一个世界模型的内部特征可映射至另一个世界模型，且性能下降有限，这为功能兼容性提供了证据。我们的研究结果表明，追求预测一致性可促进不同世界模型间形成共享的、与转移兼容的潜在结构。
英文摘要
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.
Comments18 pages, 10 figures, 2 tables. Wenhow Li and Chengwei MA contributed equally. Project page: https://sellerbubble.github.io/platonic-representation-hypothesis-on-world-models/. Corrected author metadata formatting and updated the project-page link presentation in the abstract; manuscript content and results unchanged
