@article{240721757,
  title = {Learning Video Context as Interleaved Multimodal Sequences},
  author = {Kevin Qinghong Lin and Pengchuan Zhang and Difei Gao and Xide Xia and Joya Chen and Ziteng Gao and Jinheng Xie and Xuhong Xiao and Mike Zheng Shou},
  year = {2024},
  eprint = {2407.21757},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.21757v2},
}