@article{slowfastllava15afamilyoftoken,
  title = {SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding},
  author = {Mingze Xu and Mingfei Gao and Shiyu Li and Jiasen Lu and Zhe Gan and Zhengfeng Lai and Meng Cao and Kai Kang and Yinfei Yang and Afshin Dehghan},
  year = {2025},
  eprint = {2503.18943},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.18943v2},
}