Ego-CEVR: Learning Cross-Embodiment Visual Representations from Human Egocentric Videos

Ego-CEVR is a data-native framework for hierarchical visual representation learning that assigns distinct learning objectives to global and interaction representations. The global module learns object relations, task state, and temporal progress through future prediction on egocentric video, while the Interaction module interprets wrist observations in global context and learns local alignment and contact cues through robot action supervision. The framework supports independent pretraining of its global video module on large-scale human egocentric videos and videos from diverse robot embodiments, without requiring robot action labels or paired wrist observations.