@article{visualtokencodingforvideomultimodallarge,
  title = {Visual Token Coding for Video Multimodal Large Language Models},
  author = {Chenxin Fang and Tao Chen and JunChao You and Jun Peng and Yiyi Zhou and Rongrong Ji},
  year = {2026},
  eprint = {2608.28008},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.28008},
}