@article{lian2023llmgroundedvideo,
      title={LLM-grounded Video Diffusion Models}, 
      author={Lian, Long and Shi, Baifeng and Yala, Adam and Darrell, Trevor and Li, Boyi},
      journal={arXiv preprint arXiv:2309.17444},
      year={2023},
}

@article{lian2023llmgrounded,
    title={LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models}, 
    author={Lian, Long and Li, Boyi and Yala, Adam and Darrell, Trevor},
    journal={arXiv preprint arXiv:2305.13655},
    year={2023}
}

@article{li2023gligen,
  title={GLIGEN: Open-Set Grounded Text-to-Image Generation},
  author={Li, Yuheng and Liu, Haotian and Wu, Qingyang and Mu, Fangzhou and Yang, Jianwei and Gao, Jianfeng and Li, Chunyuan and Lee, Yong Jae},
  journal={CVPR},
  year={2023}
}

@article{wang2023modelscope,
    title={Modelscope text-to-video technical report},
    author={Wang, Jiuniu and Yuan, Hangjie and Chen, Dayou and Zhang, Yingya and Wang, Xiang and Zhang, Shiwei},
    journal={arXiv preprint arXiv:2308.06571},
    year={2023}
}
@InProceedings{VideoFusion,
    author    = {Luo, Zhengxiong and Chen, Dayou and Zhang, Yingya and Huang, Yan and Wang, Liang and Shen, Yujun and Zhao, Deli and Zhou, Jingren and Tan, Tieniu},
    title     = {VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023}
}