Repository
Models / Research
ReconVLA · OpenHelix-Team
Official implementation of ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver.
Overview
Official implementation of ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver.
Review observation/action interfaces, checkpoints, robot embodiments and adaptation requirements. Repository code licensing does not automatically license weights or training data.
Project information
- Maintainer
- OpenHelix-Team
- Primary language
- Python
- Repository code license
- MIT
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2026-04-01
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
- 📊 Overview
- Getting Started <a name="installation"></a>
- Clone the Repository
- Data Preparation
- CALVIN
Browse this resource’s categories
Explore related collections
Vision-language-action models ↗More in Models
Repository
