SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models

SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models Zekun Wang author Jingchang Chen author Wangchunshu Zhou author Haichao Zhu author Jiafeng Liang author Liping Shan author Ming Liu author Dongliang Xu author Qing Yang author Bing Qin author 2024-05 text Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) Nicoletta Calzolari editor Min-Yen Kan editor Veronique Hoste editor Alessandro Lenci editor Sakriani Sakti editor Nianwen Xue editor ELRA and ICCL Torino, Italia conference publication wang-etal-2024-smarttrim https://aclanthology.org/2024.lrec-main.1300/ 2024-05 14937 14953