Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
<p align="center" width="100%">
|
| 2 |
+
<img src="https://ice.frostsky.com/2024/03/17/214a3af4a34a26be0a04e551e16b9364.webp" width="40%" height="80%">
|
| 3 |
+
</p>
|
| 4 |
+
|
| 5 |
+
# Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
|
| 6 |
+
|
| 7 |
+
### Model details:
|
| 8 |
+
|
| 9 |
+
Chain-of-Spot encourages Large Vision-Language Models to identify the region of interest (ROI) in the image condition on the question and reasoning through an interactive manner, thereby improving the ability of visual understanding.
|
| 10 |
+
|
| 11 |
+
### Where to send questions or comments about the model: https://github.com/dongyh20/Chain-of-Spot
|
| 12 |
+
|
| 13 |
+
### Paper or resources for more information: https://sites.google.com/view/chain-of-spot/
|