@article{jovaunifiedmultimodallearningforjointvid,
  title = {JoVA: Unified Multimodal Learning for Joint Video-Audio Generation},
  author = {Xiaohu Huang and Hao Zhou and Qiangpeng Yang and Shilei Wen and Kai Han},
  year = {2025},
  eprint = {2512.13677},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.13677},
}