@misc{arxiv_2609_27901,
  title = {All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation},
  author = {{Ohad Rahamim} and {Dvir Samuel} and {Idan Schwartz} and {Gal Chechik}},
  eprint = {2609.27901},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.27901}
}