Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,8 @@ It provides robust evaluation capabilities for task progress prediction and task
|
|
| 39 |
|
| 40 |
VLAC trained on 3000h+ human egocentric data, 1200h+ comprehensive public robotic manipulation data, and 15h+ self-collected manipulation data.
|
| 41 |
|
|
|
|
|
|
|
| 42 |
## ✨ Key Features
|
| 43 |
|
| 44 |
• **Pair-wise comparison mechanism** for improved progressing dense critic accuracy, better recognition of state changes, and each step can be the start of the trajectory.
|
|
|
|
| 39 |
|
| 40 |
VLAC trained on 3000h+ human egocentric data, 1200h+ comprehensive public robotic manipulation data, and 15h+ self-collected manipulation data.
|
| 41 |
|
| 42 |
+
VLAC-8B is coming soon!
|
| 43 |
+
|
| 44 |
## ✨ Key Features
|
| 45 |
|
| 46 |
• **Pair-wise comparison mechanism** for improved progressing dense critic accuracy, better recognition of state changes, and each step can be the start of the trajectory.
|