@article{fromsecondstohoursreviewingmultimodal, title = {From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding}, author = {Heqing Zou and Tianze Luo and Guiyang Xie and Victor and Zhang and Fengmao Lv and Guangcong Wang and Junyang Chen and Zhuochen Wang and Hansheng Zhang and Huaijian Zhang}, year = {2024}, eprint = {2409.18938}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2409.18938v2}, }