Article

Multi-View Latent Action Pretraining for Cross-Embodiment Robot Video Learning

The paper proposes a latent action model (LAM) that can ingest synchronized multi-camera views, using cross-attention to resolve depth and occlusion issues, then compresses them into latent actions that are fed into a policy in which a latent expert and an action expert are coupled by sequential flow matching around a frozen VLM backbone.

Part of the event: Multi-view Latent Action Pretraining Improves Cross-Embodiment Robot Policy Success Rates

This page provides a summary and source link only.