@article{seasupervisedembeddingalignmentfortoken, title = {SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs}, author = {Yuanyang Yin and Yaqi Zhao and YaJie Zhang and Ke Lin and Jiahao Wang and Xin Tao and Pengfei Wan and Di Zhang and Baoqun Yin and Wentao Zhang}, year = {2024}, eprint = {2408.11813}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2408.11813v1}, }