@article{mvpenhancingvideolargelanguagemodelsvias,
  title = {MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction},
  author = {Xiaokun Sun and Zezhong Wu and Zewen Ding and Linli Xu},
  year = {2026},
  eprint = {2601.03781},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.03781},
}