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

researchr

You are not signed in
Sign in
Sign up

Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Haichao Zhu, Jiafeng Liang, Liping Shan, Ming Liu 0004, Dongliang Xu, Qing Yang 0033, Bing Qin 0001. SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models. In Nicoletta Calzolari, Min-Yen Kan, Véronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue, editors, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024, 20-25 May, 2024, Torino, Italy. pages 14937-14953, ELRA and ICCL, 2024. [doi]

This author has not been identified. Look up 'Zekun Wang' in GoogleThis author has not been identified. Look up 'Jingchang Chen' in GoogleThis author has not been identified. Look up 'Wangchunshu Zhou' in GoogleThis author has not been identified. Look up 'Haichao Zhu' in GoogleThis author has not been identified. Look up 'Jiafeng Liang' in GoogleThis author has not been identified. Look up 'Liping Shan' in GoogleThis author has not been identified. Look up 'Ming Liu 0004' in GoogleThis author has not been identified. Look up 'Dongliang Xu' in GoogleThis author has not been identified. Look up 'Qing Yang 0033' in GoogleThis author has not been identified. Look up 'Bing Qin 0001' in Google

runs on WebDSL