@article{improvingjointaudiovideogenerationwithcr,
  title = {Improving Joint Audio-Video Generation with Cross-Modal Context Learning},
  author = {Bingqi Ma and Linlong Lang and Ming Zhang and Dailan He and Xingtong Ge and Yi Zhang and Guanglu Song and Yu Liu},
  year = {2026},
  eprint = {2603.18600},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.18600},
}