Add any-to-any pipeline tag, paper link

This PR adds a pipeline tag ensuring the model can be found at https://huggingface.co/models?pipeline_tag=any-to-any&sort=trending. It also links the model to the paper page.

README.md

@@ -15,18 +15,17 @@ language:
 - en
 metrics:
 - accuracy
-pipeline_tag: visual-question-answering
+pipeline_tag: any-to-any
 base_model:
 - Qwen/Qwen2.5-7B-Instruct
 ---
 
-
 <p align="center">
     <img src="https://cdn-uploads.huggingface.co/production/uploads/626938b16f8f86ad21deb989/tt5KYnAUmQlHtfB1-Zisl.png" width="150" style="margin-bottom: 0.2;"/>
 <p>
 
 
-<h3 align="center"><a href="https://arxiv.org/abs/2501.13106">VideoLLaMA 3: Frontier Multimodal Foundation Models for Video Understanding</a></h3>
+<h3 align="center"><a href="https://huggingface.co/papers/2501.13106">VideoLLaMA 3: Frontier Multimodal Foundation Models for Video Understanding</a></h3>
 
 <h5 align="center">