LATIDIA · Robótica
ODEWorld: una arquitectura predictiva continua a través del flujo del tiempo físico
arXiv:2607.27924v4 Tipo de anuncio: sustitución-cruce Resumen: En el mundo físico en el que vivimos, el espacio y el tiempo son fundamentalmente continuos. Sin embargo, los paradigmas de aprendizaje automático existentes para el modelado del mundo están en gran medida limitados.
WhatsApp ↗Telegram ↗
La noticia
arXiv:2607.27924v4 Announce Type: replace-cross 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,