Article

HuGe: Scaling Humanoid Generalist VLA Models with Egocentric Experience

HuGe is a family of humanoid generalist vision-language-action (VLA) models pretrained on over 2,000 hours of egocentric human and robot data. It predicts latent motion tokens to drive a pretrained whole-body controller and outputs hand-control signals.

Part of the event: Research on Pretraining HuGe Humanoid General-Purpose VLA Models

This page provides a summary and source link only.