Article
E0.5: A Geometry-Native World-Action Model Built on a 3D Foundation Model Backbone
arXiv cs.RO
The Era AI Lab team proposes E0.5, a geometry-native world-action model built directly on 3D foundation models that treats 3D geometry as the native representation for world modeling and action prediction, and explicitly predicts future 3D states and actions.
Part of the event: X-Era AI Tuoyuan Zhihui Open-Sources 4D World Action Model E0.5
This page provides a summary and source link only.