Safetensors
BaochangRen commited on
Commit
72112ac
·
verified ·
1 Parent(s): 267dc3e

update README with logo

Browse files
Files changed (1) hide show
  1. README.md +8 -1
README.md CHANGED
@@ -2,7 +2,12 @@
2
  license: mit
3
  ---
4
  <div align="center">
5
- <h1 align="center"> 🔬 LabVLA </h1>
 
 
 
 
 
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