LATIDIA · Robótica
Razonamiento latente adaptativo asistido por edge inalámbrico para modelos de visión-lenguaje-acción en IA física
arXiv:2611.19131v1 Tipo de anuncio: nuevo Resumen: Los modelos de visión-lenguaje-acción (VLA) permiten la inteligencia artificial (IA) encarnada al traducir las observaciones visuales y las instrucciones lingüísticas en acciones robóticas. Emergentes
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.19131v1 Announce Type: new Abstract: Vision-language-action (VLA) models enable embodied artificial intelligence (AI) by translating visual observations and language instructions into robotic actions. Emerging use cases in physical AI are expected to drive the need for efficient inference and communication, as the computational demands of the VLA models pose challenges for real-time control with limited onboard resources. Test-time scaling through latent reasoning allows these models to refine hidden representations without generating explicit chain-of-thought (CoT) tokens, but introduces a trade-off between task success, inference latency, and energy consumption. In this paper, we address the efficient collaborative inference under a realistic communication scenario. We propose a wireless edge-assisted framework for adaptive latent