@inproceedings{tkeff2025,
  title = {{STORM}: Token-Efficient Long Video Understanding for Multimodal LLMs},
  author = {Jindong Jiang and Xiuyu Li and Zhijian Liu and Muyang Li and Guo Chen and Zhiqi Li and De-An Huang and Guilin Liu and Zhiding Yu and Kurt Keutzer and Sungjin Ahn and Jan Kautz and Hongxu Yin and Yao Lu and Song Han and Wonmin Byeon},
  year = {2025},
  month = {October},
  booktitle = {ICCV Workshop on Closing the Loop Between Vision and Language (CLVL)},
  doi = {10.1109/ICCVW69036.2025.00614},
  eprint = {2503.04130},
  archiveprefix = {arxiv},
}
