Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,8 @@ datasets:
|
|
| 16 |
- allenai/MolmoAct2-LIBERO-Dataset
|
| 17 |
---
|
| 18 |
|
|
|
|
|
|
|
| 19 |
**RIO-2**
|
| 20 |
|
| 21 |
RIO-2 is a two-rate WAM(World Action Model) built for robotics. RIO-2 is composed with a low-frequency visual-language S2 backbone and a high-frequency JEPA-diffusion S1 action policy. The model is designed to separate slow scene understanding from fast robot control:
|
|
|
|
| 16 |
- allenai/MolmoAct2-LIBERO-Dataset
|
| 17 |
---
|
| 18 |
|
| 19 |
+
|
| 20 |
+
|
| 21 |
**RIO-2**
|
| 22 |
|
| 23 |
RIO-2 is a two-rate WAM(World Action Model) built for robotics. RIO-2 is composed with a low-frequency visual-language S2 backbone and a high-frequency JEPA-diffusion S1 action policy. The model is designed to separate slow scene understanding from fast robot control:
|