LATIDIA · Robótica

$\Delta$ Flow Matching para modelos de cimentación de robots

arXiv:2610.15794v1 Announce Type: new Abstract: Flow matching is a common generative recipe for robot foundation models. Los modelos de visión-lenguaje-acción (VLA) generan fragmentos de acción, mientras que los modelos de acción mundial (WAM) añaden

La noticia

arXiv:2610.15794v1 Announce Type: new Abstract: Flow matching is a common generative recipe for robot foundation models. Vision-language-action models (VLAs) generate action chunks, while world-action models (WAMs) additionally generate future visual states. Both start generation from a fixed Gaussian prior, despite temporal continuity between past and future states and actions. This requires costly training and iterative sampling, especially for WAMs with an additional visual branch. We introduce $\Delta$-flow, which constructs the source from recent history with mild noise rather than from a fixed Gaussian prior. This moves the source closer to the target, reducing transport to a small residual $\Delta$ that can be learned efficiently and enables single-step inference. We integrate