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

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/hwridl7ipfj564witz2ydgl0r
- Original: https://arxiv.org/abs/2610.27794

## Summary

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.