@article{omnivaeanaudiovideovaewithcrossmodalalig,
  title = {OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation},
  author = {Jun Zhan and Chen Yang and Yitian Gong and Donghua Yu and Kuangwei Chen and Wenbo Zhang and Kexin Huang and Qi Luo and Zhe Xu and Ying Zhu and Jin Wang and Tengyue Zhang and Qi Chen and Cheng Chang and Songlin Wang and Junqi Dai and Jiasheng Ye and Xiaogui Yang and Tianyi Liang and Xiangyu Peng and Zhaoye Fei and Shimin Li and Qinyuan Cheng and Xie Chen and Xinchi Chen and Xipeng Qiu},
  year = {2026},
  eprint = {2607.23855},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.23855},
}