ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

odeworld:-a-continuous-predictive-architecture-via-physical-time-flow

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

[Submitted on 30 Jul 2026 (v1), last revised 15 Nov 2026 (this version, v4)]

View PDF HTML (experimental)

Abstract: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: this https URL.

Submission history

From: Haoyi Niu [view email]
[v1] Thu, 30 Jul 2026 09:37:30 UTC (5,284 KB)
[v2] Fri, 7 Aug 2026 03:27:58 UTC (5,284 KB)
[v3] Fri, 14 Aug 2026 23:51:40 UTC (5,280 KB)
[v4] Sun, 15 Nov 2026 23:45:35 UTC (5,314 KB)