Add model card, link to paper and pipeline tag
Browse filesThis PR ensures the model can be found at https://huggingface.co/papers/2412.03704.
README.md
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: image-text-to-text
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
This repository contains the VisVM model described in [Scaling Inference-Time Search with Vision Value Model for Improved Visual Comprehension](https://huggingface.co/papers/2412.03704).
|
| 6 |
+
|
| 7 |
+
Code: https://github.com/si0wang/VisVM
|