To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models

To Preserve or To Compress: An In-Depth Study of Connector Selection in Multimodal Large Language Models Junyan Lin author Haoran Chen author Dawei Zhu author Xiaoyu Shen author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication lin-etal-2024-preserve 10.18653/v1/2024.emnlp-main.325 https://aclanthology.org/2024.emnlp-main.325/ 2024-11 5666 5680