LATIDIA · Robótica

Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors

arXiv: 2610.15556v1Tipo de Anuncio: Cross Resumen: Los modelos de Visión-Lenguaje-Acción (VLA) comúnmente generan acciones de robot token por token a través de decodificadores de Modelo de Lenguaje Grande (LLM), lo que hace que la latencia de inferencia crezca con Act

La noticia

arXiv:2610.15556v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models commonly generate robot actions token by token through Large Language Model (LLM) decoders, causing inference latency to grow with action sequence length and limiting closed-loop control frequency. We present Goal-Conditioned Vision-Predictor-Action (VPA), which replaces autoregressive decoders with a lightweight latent control loop. A shared vision encoder and a frozen text encoder embed observations, goal images, and instructions; a neuro-symbolic selector chooses a discrete skill; a Joint-Embedding Predictive Architecture (JEPA) predictor forecasts the next latent state; and a flow-matching solver generates an entire action chunk in a few integration steps, so that sequential network evaluations per decision step do not depend on the