SOURCE-LINKED INTELLIGENCE

AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Embodied foundation models are constrained by the limited scale and diversity of robot demonstrations, motivating the use of large-scale egocentric human interaction data. However, how to effectively incorporate such data into embodied-model pre-training remains unclear because of substantial embodiment and action-space gaps between humans and robots. We present AtomEgo, a systematic study of ego--robot co-training supported by a curated corpus of approximately 2,659 hours and a scalable data processing pipeline. Across vision--language--action and world--action model architectures, we investi

Read original source ↗ Open in workspace

recordType

paper

region

Global