@misc{zohar2024apollo, title={Apollo: An Exploration of Video Understanding in Large Multimodal Models}, author={Orr Zohar and Xiaohan Wang and Yann Dubois and Nikhil Mehta and Tong Xiao and Philippe Hansen-Estruch and Licheng Yu and Xiaofang Wang and Felix Juefei-Xu and Ning Zhang and Serena Yeung-Levy and Xide Xia}, year={2024}, eprint={2412.10360}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2412.10360} }