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 Lead ^‡ Corresponding Authors

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.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for csuhan/TA-Tok

Base model

google/siglip2-so400m-patch14-384

Finetuned

(15)

this model

Spaces using csuhan/TA-Tok 2

Paper for csuhan/TA-Tok

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Paper • 2506.18898 • Published Jun 23, 2025 • 33