@misc{ranasinghe2024understanding,
      title={Understanding Long Videos in One Multimodal Language Model Pass}, 
      author={Kanchana Ranasinghe and Xiang Li and Kumara Kahatapitiya and Michael S. Ryoo},
      year={2024},
      eprint={2403.16998},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}