---
title: Tar-TA-Tok
canonical_url: "https://www.modelscope.cn/models/bytedance-community/Tar-TA-Tok"
md_url: "https://www.modelscope.cn/models/bytedance-community/Tar-TA-Tok.md"
repository: bytedance-community/Tar-TA-Tok
last_updated: 2026-06-05
license: apache-2.0
base_model:
  - google/siglip2-so400m-patch14-384
base_model_relation: finetune
library_name:
  - pytorch
frameworks:
  - pytorch
downloads: 0
stars: 0
---

# Tar-TA-Tok

> Tar-TA-Tok - bytedance-community 在 ModelScope 开源的模型。Unifying Visual Understanding and Generation via Text-Aligned Representations Jiaming Han, Hao Chen † , Yang Zhao, Hanyu Wang, Qi Zhao, Ziyan Yang, Hao He, Xiangyu Yue ‡ , Lu Jiang ‡ † Project…

bytedance-community/Tar-TA-Tok 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可，基于 google/siglip2-so400m-patch14-384 构建。

- **Repository**: bytedance-community/Tar-TA-Tok
- **License**: apache-2.0
- **Base model**: google/siglip2-so400m-patch14-384
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-06-05

Source: https://www.modelscope.cn/models/bytedance-community/Tar-TA-Tok

---

### Unifying Visual Understanding and Generation via Text-Aligned Representations
> [Jiaming Han](https://csuhan.com), [Hao Chen](https://haochen-rye.github.io)<sup>†</sup>, [Yang Zhao](https://scholar.google.com/citations?user=uPmTOHAAAAAJ&hl=zh-CN), [Hanyu Wang](https://hywang66.github.io), [Qi Zhao](https://kevinz8866.github.io), [Ziyan Yang](https://ziyanyang.github.io), [Hao He](https://hehao13.github.io), [Xiangyu Yue](https://xyue.io)<sup>‡</sup>, [Lu Jiang](https://www.lujiang.info)<sup>‡</sup>
>
> <sup>†</sup> Project Lead&nbsp;&nbsp;<sup>‡</sup> Corresponding Authors

 <a href="https://tar.csuhan.com">
    <img
      src="https://img.shields.io/badge/Project-Page-0A66C2?logo=chromewebstore&logoColor=0A66C2"
      alt="Project Page"
    />
  </a>
<a href="http://arxiv.org/abs/2506.18898">
    <img
      src="https://img.shields.io/badge/arXiv-Paper-red?logo=arxiv&logoColor=red"
      alt="Tar Paper on arXiv"
    />
  </a>
  <a href="https://huggingface.co/collections/csuhan/tar-68538273b5537d0bee712648">
    <img 
        src="https://img.shields.io/badge/HF-Model-yellow?logo=huggingface&logoColor=yellow" 
        alt="Huggingface Model"
    />
  </a>
  <a href="https://huggingface.co/spaces/csuhan/Tar-7B">
    <img 
        src="https://img.shields.io/badge/HF-Space1-yellow?logo=huggingface&logoColor=yellow" 
        alt="Huggingface Space"
    />
  </a>
  <a href="https://huggingface.co/spaces/csuhan/Tar">
    <img 
        src="https://img.shields.io/badge/HF-Space2-yellow?logo=huggingface&logoColor=yellow" 
        alt="Huggingface Space"
    />
  </a>


<img src="asset/demos.png" width="80%">


### Citation
```
@article{han2025tar,
  title={Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations}, 
  author={Han, Jiaming and Chen, Hao and Zhao, Yang and Wang, Hanyu and Zhao, Qi and Yang, Ziyan and He, Hao and Yue, Xiangyu and Jiang, Lu},
  journal={arXiv preprint arXiv:2506.18898},
  year={2025},
}
```

### License
This project is licensed under the Apache 2.0 License.