update README with logo
Browse files
README.md
CHANGED
|
@@ -2,7 +2,12 @@
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
<div align="center">
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
<h3 align="center"> Grounding Vision–Language–Action Models in Scientific Laboratories </h3>
|
| 7 |
|
| 8 |
<p align="center">
|
|
@@ -18,6 +23,8 @@ license: mit
|
|
| 18 |
|
| 19 |
**LabVLA** is the first vision–language–action (VLA) model designed for scientific laboratory environments. It combines a **Qwen3-VL-4B** vision–language backbone with a **DiT flow-matching action expert**, trained with the π0.5 recipe to enable real-time robot control in lab settings.
|
| 20 |
|
|
|
|
|
|
|
| 21 |
## How to Use
|
| 22 |
|
| 23 |
### Download
|
|
|
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
<div align="center">
|
| 5 |
+
|
| 6 |
+
<p align="center">
|
| 7 |
+
<img src="https://raw.githubusercontent.com/zjunlp/LabVLA/main/assets/logo/labvla-symbol.png" width="88" alt="LabVLA symbol" />
|
| 8 |
+
<img src="https://raw.githubusercontent.com/zjunlp/LabVLA/main/assets/logo/labvla-wordmark.png" height="56" alt="LabVLA" />
|
| 9 |
+
</p>
|
| 10 |
+
|
| 11 |
<h3 align="center"> Grounding Vision–Language–Action Models in Scientific Laboratories </h3>
|
| 12 |
|
| 13 |
<p align="center">
|
|
|
|
| 23 |
|
| 24 |
**LabVLA** is the first vision–language–action (VLA) model designed for scientific laboratory environments. It combines a **Qwen3-VL-4B** vision–language backbone with a **DiT flow-matching action expert**, trained with the π0.5 recipe to enable real-time robot control in lab settings.
|
| 25 |
|
| 26 |
+
The checkpoint is **self-contained** — loading requires no external base model. The bundled `vlm_config.json` allows the backbone to be rebuilt weightlessly, and `model.safetensors` provides all weights.
|
| 27 |
+
|
| 28 |
## How to Use
|
| 29 |
|
| 30 |
### Download
|