@article{yin2025best, title={The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video Generation}, author={Yin, Aoxiong and Shen, Kai and Leng, Yichong and Tan, Xu and Zhou, Xinyu and Li, Juncheng and Tang, Siliang}, journal={arXiv preprint arXiv:2503.04606}, year={2025} }