Загрузка видео...
Не удалось загрузить видео
New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.
20,458 просмотров • 1 год назад •via X (Twitter)
Комментарии: 4

The Humanoid Hub1 год назад
Detailed insights in this thread:

AssemblyAI1 год назад
Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

AI Expert Khalid1 год назад
I'm fascinated by the potential of NaVILA to revolutionize robot navigation! Imagine instructing robots with just natural language. Pure adrenaline!

maru1 год назад
It sounds like
