Add pipeline tag and paper page link
Browse filesThis PR adds the missing `pipeline_tag` to make the model discoverable in the hub and links the card to the corresponding Hugging Face paper page.
README.md
CHANGED
|
@@ -1,20 +1,16 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
# Video-Coder SFT Model
|
| 7 |
|
| 8 |
-
|
| 9 |
-
This repository contains the Video-Coder-SFT-9B for [Video-Coder: Reinforcing Agentic Coding for Video Generation](https://arxiv.org/abs/2611.09894).
|
| 10 |
-
|
| 11 |
|
| 12 |
[**🌐 Project Page**](https://cywang735.github.io/Video-Coder/) | [**📖 Paper**](https://arxiv.org/abs/2611.09894) | [**💻 Code**](https://github.com/CYWang735/Video-Coder)
|
| 13 |
|
| 14 |
-
|
| 15 |
# 👀 Intro
|
| 16 |
|
| 17 |
-
|
| 18 |
<div align="center">
|
| 19 |
<img src="https://raw.githubusercontent.com/CYWang735/Video-Coder/main/assets/teaser.png" alt="Video-Coder Overview" width="80%">
|
| 20 |
</div>
|
|
@@ -32,22 +28,16 @@ and execution feedback for agent training and inference.
|
|
| 32 |
Video-Coder achieves significant gains,
|
| 33 |
improving Minimax-H3 by **approximately 7 points on PhyGenBench and 24 points on VBench-2.0**.
|
| 34 |
|
| 35 |
-
|
| 36 |
## 🎥 Demo
|
| 37 |
|
| 38 |
-
|
| 39 |
<div align="center">
|
| 40 |
<img src="https://raw.githubusercontent.com/CYWang735/Video-Coder/main/assets/qualitative.png" alt="Inference Process" width="85%">
|
| 41 |
</div>
|
| 42 |
|
| 43 |
-
|
| 44 |
## Citation
|
| 45 |
|
| 46 |
-
|
| 47 |
If you find this work helpful for your research, please consider citing:
|
| 48 |
|
| 49 |
-
|
| 50 |
```bibtex
|
| 51 |
|
| 52 |
-
|
| 53 |
```
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
---
|
| 5 |
|
|
|
|
| 6 |
# Video-Coder SFT Model
|
| 7 |
|
| 8 |
+
This repository contains the Video-Coder-SFT-9B for [Video-Coder: Reinforcing Agentic Coding for Video Generation](https://huggingface.co/papers/2611.09894).
|
|
|
|
|
|
|
| 9 |
|
| 10 |
[**🌐 Project Page**](https://cywang735.github.io/Video-Coder/) | [**📖 Paper**](https://arxiv.org/abs/2611.09894) | [**💻 Code**](https://github.com/CYWang735/Video-Coder)
|
| 11 |
|
|
|
|
| 12 |
# 👀 Intro
|
| 13 |
|
|
|
|
| 14 |
<div align="center">
|
| 15 |
<img src="https://raw.githubusercontent.com/CYWang735/Video-Coder/main/assets/teaser.png" alt="Video-Coder Overview" width="80%">
|
| 16 |
</div>
|
|
|
|
| 28 |
Video-Coder achieves significant gains,
|
| 29 |
improving Minimax-H3 by **approximately 7 points on PhyGenBench and 24 points on VBench-2.0**.
|
| 30 |
|
|
|
|
| 31 |
## 🎥 Demo
|
| 32 |
|
|
|
|
| 33 |
<div align="center">
|
| 34 |
<img src="https://raw.githubusercontent.com/CYWang735/Video-Coder/main/assets/qualitative.png" alt="Inference Process" width="85%">
|
| 35 |
</div>
|
| 36 |
|
|
|
|
| 37 |
## Citation
|
| 38 |
|
|
|
|
| 39 |
If you find this work helpful for your research, please consider citing:
|
| 40 |
|
|
|
|
| 41 |
```bibtex
|
| 42 |
|
|
|
|
| 43 |
```
|