克隆确定性世界：潜空间几何在长时程世界模型中的关键作用
Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models
论文揭示潜空间几何结构是长时程世界模型保真度的瓶颈，并提出时序对比学习作为几何正则化手段，可无缝集成到标准自编码器中。这对视觉世界模型、视频预测等任务中表征学习的设计具有直接启发，即通过对比约束塑造反映物理状态流形的潜空间。
原文依据 the primary bottleneck for long-horizon fidelity is the geometric structure of the latent representation, not the dynamics model itself
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论世界模型是一种模拟世界如何演化的内部模型。给定过去的观测和动作，它预测具身智能体及其环境的未来物理状态。准确的世界模型对于智能体在复杂动态环境中有效思考、规划和推理至关重要。然而，现有世界模型往往侧重于开放世界的随机生成，而忽视了对确定性场景（如固定地图迷宫和静态空间机器人导航）进行高保真建模的需求。在本工作中，我们通过解决一个基础但开放的问题——构建一个能够完全克隆确定性世界的模型——朝着构建真正准确的世界模型迈出了一步。1）通过诊断实验，我们定量证明了高保真克隆是可行的，并且长时程保真度的主要瓶颈是潜表示的几何结构，而非动力学模型本身。2）基于这一洞见，我们表明应用时序对比学习原理作为几何正则化，可以有效地构建一个更好地反映底层物理状态流形的潜空间，证明对比约束可以作为稳定世界建模的强大归纳偏置；我们将此方法称为几何正则化世界模型（GRWM）。其核心是一个轻量级几何正则化模块，可以无缝集成到标准自编码器中，重塑其潜空间，为有效的动力学建模提供稳定基础。通过关注表示质量，GRWM 提供了一个简单而强大的流程来提高世界模型的保真度。代码可在 https://github.com/XiaFire/Clone_Deterministic_Environment 获取。
英文原文摘要 1778 字符
A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. Accurate world models are essential for enabling agents to think, plan, and reason effectively in complex, dynamic settings. However, existing world models often focus on random generation of open worlds, but neglect the need for high-fidelity modeling of deterministic scenarios (such as fixed-map mazes and static space robot navigation). In this work, we take a step toward building a truly accurate world model by addressing a fundamental yet open problem: constructing a model that can fully clone a deterministic world. 1) Through diagnostic experiment, we quantitatively demonstrate that high-fidelity cloning is feasible and the primary bottleneck for long-horizon fidelity is the geometric structure of the latent representation, not the dynamics model itself. 2) Building on this insight, we show that applying temporal contrastive learning principle as a geometric regularization can effectively curate a latent space that better reflects the underlying physical state manifold, demonstrating that contrastive constraints can serve as a powerful inductive bias for stable world modeling; we call this approach Geometrically-Regularized World Models (GRWM). At its core is a lightweight geometric regularization module that can be seamlessly integrated into standard autoencoders, reshaping their latent space to provide a stable foundation for effective dynamics modeling. By focusing on representation quality, GRWM offers a simple yet powerful pipeline for improving world model fidelity. Code is available at https://github.com/XiaFire/Clone_Deterministic_Environment.