Large Multimodal Model Compression via Iterative Efficient Pruning and Distillation.

@inproceedings{wang-2024-large, author = {Maolin Wang and Yao Zhao and Jiajia Liu and Jingdong Chen and Chenyi Zhuang and Jinjie Gu and Ruocheng Guo and Xiangyu Zhao}, editor = {Tat-Seng Chua and Chong-Wah Ngo and Roy Ka-Wei Lee and Ravi Kumar and Hady Wirawan Lauw}, title = {{Large Multimodal Model Compression via Iterative Efficient Pruning and Distillation}}, booktitle = {{Companion Proceedings of the ACM on Web Conference 2024, WWW 2024, Singapore, Singapore, May 13-17, 2024}}, pages = {235--244}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3589335.3648321}, doi = {https://doi.org/10.1145/3589335.3648321} }