Update README.md
Browse files
README.md
CHANGED
|
@@ -31,3 +31,4 @@ filtered 75K QA dataset as the training set, we obtained a highly capable captio
|
|
| 31 |
* **Detailed description for natural images**: The outputs of CapRL-3B can perfectly cover all valid visual information while containing fewer hallucinations.
|
| 32 |
|
| 33 |
## Cases
|
|
|
|
|
|
| 31 |
* **Detailed description for natural images**: The outputs of CapRL-3B can perfectly cover all valid visual information while containing fewer hallucinations.
|
| 32 |
|
| 33 |
## Cases
|
| 34 |
+
|