File size: 672 Bytes
73a6d10 |
1 2 3 4 5 6 7 8 9 10 11 12 13 |
<p align="center" width="100%">
<img src="https://ice.frostsky.com/2024/03/17/214a3af4a34a26be0a04e551e16b9364.webp" width="40%" height="80%">
</p>
# Chain-of-Spot: Interactive Reasoning Improves Large Vision-Language Models
### Model details:
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.
### Where to send questions or comments about the model: https://github.com/dongyh20/Chain-of-Spot
### Paper or resources for more information: https://sites.google.com/view/chain-of-spot/ |