@article{231110122v3, title = {Video-LLaVA: Learning United Visual Representation by Alignment Before Projection}, author = {Bin Lin and Yang Ye and Bin Zhu and Jiaxi Cui and Munan Ning and Peng Jin and Li Yuan}, year = {2023}, eprint = {2311.10122}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2311.10122v3}, }