Refine model card content and add pipeline tag

This PR refines the model card by:
- Adding the `pipeline_tag: any-to-any` to the metadata, ensuring better discoverability for users interested in multimodal translation tasks.
- Replacing the full paper abstract with a concise introduction, adhering to the best practice of keeping model cards brief and to the explicit instruction not to include the full abstract.

README.md

@@ -7,6 +7,7 @@ tags:
 - Video Generation
 - Vision Translation
 - Bridge Model
+pipeline_tag: any-to-any
 ---
 
 # 🎥 ViBT: Vision Bridge Transformer at Scale  
@@ -17,4 +18,4 @@ tags:
 <a href="https://github.com/Yuanshi9815/ViBT"><img src="https://img.shields.io/badge/GitHub-Code-blue.svg?logo=github&" alt="GitHub"></a>
 </div>
 
-We introduce **Vision Bridge Transformer (ViBT)**, a large-scale instantiation of Brownian Bridge Models designed for conditional generation. Unlike traditional diffusion models that transform noise into data, Bridge Models directly model the trajectory between inputs and outputs, creating an efficient data-to-data translation paradigm. By scaling these models to 20B and 1.3B parameters, we demonstrate their effectiveness for image and video translation tasks. To support this scale, we adopt a Transformer architecture and propose a variance-stabilized velocity-matching objective for robust training. Together, these advances highlight the power of scaling Bridge Models for instruction-based image editing and complex video translation.
+This repository introduces **Vision Bridge Transformer (ViBT)**, a large-scale instantiation of Brownian Bridge Models designed for efficient conditional generation. ViBT directly models the trajectory between inputs and outputs, creating an efficient data-to-data translation paradigm. The models demonstrate effectiveness for various image and video translation tasks, including instruction-based image editing and complex video translation.