Article

EXE: Egocentric Cross-Embodiment Pretraining with Factorized Latent Actions for VLA Models

EXE is an egocentric cross-embodiment pretraining framework that learns factorized latent action representations from human manipulation videos, separating shared manipulation priors from embodiment-specific signals. The authors state that this shared action space lets robot policies acquire generalizable manipulation semantics from diverse human demonstrations, and that the same pretraining can be used for both parallel grippers and dexterous hands. On RoboTwin 2.0, RoboCasa GR1, and real-world manipulation tasks, EXE achieves consistent improvements over baselines without pretraining.

Part of the event: EXE: Cross-Embodiment Egocentric Video Pretraining for VLA

This page provides a summary and source link only.