Authors

Michael Rabbat

Publications 2

Preprint Open access

Cross-Embodiment Robot Foundation World Models with Latent Actions

Huang Huang, Sriram Yenamandra, Arjun Majumdar et al. · 2026

The diversity of robot embodiments and action spaces makes it challenging to build robot world models that generalize across different embodiments. We introduce the Latent Action-Conditioned Robot World Model (LAC-WM), which operates within a learned unified latent action space shared across diverse embodiments. This u …

Preprint Open access

H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning

Wancong Zhang, Basile Terver, Michael Rabbat et al. · 2026

Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models predict and plan at a single timescale or with multiple horizons in one shared latent space. We introduce H-JEPA, an end-to-end recipe for training a hierarchy of actio …

Co-authors