@article{vimigroundingvideogenerationthroughmulti,
  title = {VIMI: Grounding Video Generation through Multi-modal Instruction},
  author = {Yuwei Fang and Willi Menapace and Aliaksandr Siarohin and Tsai-Shien Chen and Kuan-Chien Wang and Ivan Skorokhodov and Graham Neubig and Sergey Tulyakov},
  year = {2024},
  eprint = {2407.06304},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.06304v1},
}