@article{towardseffectivelongvideounderstandingof,
  title = {Towards Effective Long Video Understanding of Multimodal Large Language Models via One-shot Clip Retrieval},
  author = {Tao Chen and Shaobo Ju and Qiong Wu and Chenxin Fang and Kun Zhang and Jun Peng and Hui Li and Yiyi Zhou and Rongrong Ji},
  year = {2025},
  eprint = {2512.08410},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2512.08410},
}