Article

SkeLAM: A Robot World Model Using Skeleton-Supervised Latent Actions for Zero-Shot Cross-Embodiment Transfer

Harbin Institute of Technology (Shenzhen), the National University of Singapore, and other institutions propose SkeLAM, built on Cosmos-Predict2.5-2B and trained on about 10 hours of robot interaction data, using robot skeletons to supervise latent actions in video.

Part of the event: SkeLAM: A Robot World Model with Skeleton-Supervised Latent Actions

This page provides a summary and source link only.