流等变世界模型：部分可观测动态环境中的记忆机制

Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments

January 3, 2026

作者: Hansen Jin Lillemark, Benhao Huang, Fangneng Zhan, Yilun Du, Thomas Anderson Keller

cs.AI

摘要

具身系统将世界体验为“流动的交响乐”：多种持续感官输入流与自主动作相结合，并与外部物体动态交织而成的组合。这些流遵循平滑的时间参数化对称性，通过精妙构建的代数体系融合；然而大多数神经网络世界模型忽视这种结构，转而从数据中重复学习相同变换。本研究提出“流等变世界模型”，将自主运动与外部物体运动统一为单参数李群“流”。我们利用这种统一性实现对上述变换的群等变处理，从而构建出数百个时间步内稳定的潜在世界表征。在2D和3D部分可观测视频世界建模基准测试中，流等变世界模型显著优于同类基于扩散和记忆增强的先进架构——尤其在智能体当前视野外存在可预测世界动态时表现突出。研究表明流等变特性对长程推演尤为有利，其泛化能力远超训练时域。通过基于内外运动构建世界模型表征，流等变为实现数据高效、对称性引导的具身智能开辟了可扩展路径。项目链接：https://flowequivariantworldmodels.github.io。

English

Embodied systems experience the world as 'a symphony of flows': a combination of many continuous streams of sensory input coupled to self-motion, interwoven with the dynamics of external objects. These streams obey smooth, time-parameterized symmetries, which combine through a precisely structured algebra; yet most neural network world models ignore this structure and instead repeatedly re-learn the same transformations from data. In this work, we introduce 'Flow Equivariant World Models', a framework in which both self-motion and external object motion are unified as one-parameter Lie group 'flows'. We leverage this unification to implement group equivariance with respect to these transformations, thereby providing a stable latent world representation over hundreds of timesteps. On both 2D and 3D partially observed video world modeling benchmarks, we demonstrate that Flow Equivariant World Models significantly outperform comparable state-of-the-art diffusion-based and memory-augmented world modeling architectures -- particularly when there are predictable world dynamics outside the agent's current field of view. We show that flow equivariance is particularly beneficial for long rollouts, generalizing far beyond the training horizon. By structuring world model representations with respect to internal and external motion, flow equivariance charts a scalable route to data efficient, symmetry-guided, embodied intelligence. Project link: https://flowequivariantworldmodels.github.io.