RESEARCH PAPERSubmitted 4 Mar 2026

MEM: Multi-Scale Embodied Memory for Vision Language Action Models

Marcel Torne; Karl Pertsch; Homer Walke; Kyle Vedder; Suraj Nair; Brian Ichter; Allen Z. Ren; Haohuan Wang; Jiaming Tang; Kyle Stachowicz; Karan Dhabalia; Michael Equi; Quan Vuong; Jost Tobias Springenberg; Sergey Levine; Chelsea Finn; Danny Driess

Read on arXiv PDF Project page

Classification

View four quadrants

Major category: VLA
Quadrant: Not applicable
Architecture: Dual-system
Prediction paradigm: Not applicable
Subcategories: Memory & long-horizon VLA Hierarchical & dual-system VLA
Source review status: Verified from primary sources

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@article{torne2026mem,
  title={MEM: Multi-Scale Embodied Memory for Vision Language Action Models},
  author={Torne, Marcel and Pertsch, Karl and Walke, Homer and Vedder, Kyle and Nair, Suraj and Ichter, Brian and Ren, Allen Z. and Wang, Haohuan and Tang, Jiaming and Stachowicz, Kyle and Dhabalia, Karan and Equi, Michael and Vuong, Quan and Springenberg, Jost Tobias and Levine, Sergey and Finn, Chelsea and Driess, Danny},
  journal={arXiv:2603.03596},
  year={2026}
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models

What Matters for Latent Actions in Robot Learning

SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation