@article{241205185v2,
  title = {LinVT: Empower Your Image-level Large Language Model to Understand Videos},
  author = {Lishuai Gao and Yujie Zhong and Yingsen Zeng and Haoxian Tan and Dengjie Li and Zheng Zhao},
  year = {2024},
  eprint = {2412.05185},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.05185v2},
}