# Physical Intelligence proposes MEM, enabling π0.6's VLA to remember long-horizon tasks of up to 15 minutes

- Source: Physical Intelligence
- Published: 2026-03-02T16:00:00.000Z
- RoboHot: https://robohot.news/en/items/fb60b7s19mppw7uglnkfpt8gl
- Original: https://www.pi.website/research/memory

## Summary

Physical Intelligence proposed a method called Multi-scale Embodied Memory (MEM) that provides vision-language-action models (VLAs) with both short-term and long-term memory, enabling the model to complete tasks lasting up to 15 minutes, such as cleaning an entire kitchen or making a grilled cheese sandwich from scratch.

## Why it matters

The article identifies memory mechanisms as the bottleneck for long-horizon tasks and presents a dual-scale design that stores video for the short term and language for the long term, an approach that can be transferred to other work.