@inproceedings{fan2026flashvid,
  title={FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging},
  author={Fan, Ziyang and Li, Yulin and Xing, Ruilong and Chen, Keyu and Jiang, Li and Tian, Zhuotao},
  booktitle={ICLR},
  year={2026}
}