@article{catpcrossattentiontokenpruningfor, title = {CATP: Cross-Attention Token Pruning for Accuracy Preserved Multimodal Model Inference}, author = {Ruqi Liao and Chuqing Zhao and Jin Li and Weiqi Feng}, year = {2024}, eprint = {2404.08567}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.08567v1}, }