Physical Intelligence reports a VLA trained with RECAP to improve through autonomous experience and expert corrections.
A newer version is available: π₀.₇ ↗
Access and availability
- Code
- Awaiting verification
- Model files
- Download information awaiting verification
- Training data
- Awaiting verification
API access awaiting verification
Release information
Source ↗Verified on · 2026-10-23
At a glance
- Model type
- Vision-language-action
- Released
- November 17, 2025
Awaiting verification · 4
Architecture · Weight parameters · Input · Output
Related robots
No sourced capability or robot usage evidence is recorded for this version yet.
Other versions in this model family
Family and other-version demonstrations are context, not independently verified results for the selected weights.
Before you use this version: Available weights or code do not establish plug-and-play robot compatibility. Check the required configuration, data and interfaces in the source documentation.
Submit a source or correction