@article{flashslothlightningmultimodallarge, title = {FlashSloth: Lightning Multimodal Large Language Models via Embedded Visual Compression}, author = {Bo Tong and Bokai Lai and Yiyi Zhou and Gen Luo and Yunhang Shen and Ke Li and Xiaoshuai Sun and Rongrong Ji}, year = {2024}, eprint = {2412.04317}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2412.04317v1}, }