ODEWorld：一种基于物理时间流的连续预测架构
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
- Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））
- Berkeley Artificial Intelligence Research (BAIR), University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究院（BAIR））
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究针对现有世界建模机器学习范式局限于离散时间预测的问题，提出基于PT-Flow的连续时间潜在世界模型ODEWorld，解决表示崩溃问题，在视频生成和机器人控制任务中表现出色。
AI中文摘要：
我们所处的物理世界中，空间与时间本质上是连续的，但现有用于世界建模的机器学习范式大多局限于离散时间预测，在捕捉物理世界动态时存在显著效率不足。我们提出一种名为物理时间流（Physical-Time Flow，PT-Flow）的新方法，该方法学习在物理时间中运行的连续潜在速度场，关键在于将序列数据的底层动态参数化为嵌入结构良好的表示空间中的常微分方程（Ordinary Differential Equation，ODE）。在该范式下，未来预测可转化为压缩潜在空间中通过ODE求解器进行的时间积分。基于PT-Flow，我们构建了连续时间潜在世界模型ODEWorld，该模型兼具高效性与通用性。ODEWorld通过提取时变特征并在动态表示空间和潜在速度场上施加ODE属性，有效解决了潜在世界模型研究中长期存在的表示崩溃问题，这也使其即便在长期预测后仍能实现高质量图像重建。此外，其连续特性支持任意时间分辨率，甚至可进行反向预测，而这是大多数离散时间模型无法实现的。最后，ODEWorld能提供丰富的面向规划的信息，以促进下游策略学习。大量实验表明，ODEWorld成功调和了利于规划的动态抽象与视觉真实性，在视频生成和机器人控制任务中均表现出色。项目网站：this https URL
英文摘要：
In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time prediction, thereby exhibiting significant inefficiency in capturing the dynamics of physical world. We introduce Physical-Time Flow (PT-Flow), a novel approach that learns a continuous latent velocity field operating in physical time. Crucially, the underlying dynamics of sequential data are parameterized by an ordinary differential equation (ODE) embedded in a well-structured representation space. Under this paradigm, the prediction of future can be recast as temporal integration via an ODE solver in the compressed latent space. Building upon PT-Flow, we construct ODEWorld, a continuous-time latent world model that is both efficient and versatile. By extracting time-variant features and enforcing ODE properties on both the dynamical representation space and the latent velocity field, ODEWorld effectively addresses the long-standing representation collapse issue in latent world model literature. This also enables high-quality image reconstruction even after long-horizon prediction. Moreover, its continuous nature allows for arbitrary temporal resolution and even backward prediction, which is impossible for most discrete-time models. Lastly, ODEWorld can provide rich planning-oriented information to facilitate downstream policy learning. Comprehensive experiments demonstrate that ODEWorld successfully reconciles planning-conducive dynamics abstraction with visual realism, excelling in both video generation and robotic control. Project page: https://dstate.github.io/odeworld_website/.
