ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning.

LiQun Huang Wen Luo Peng Chen Xiaotao Huang LiQun Huang ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning. 24151-24159 2026 AAAI https://doi.org/10.1609/aaai.v40i29.39594 conf/aaai/2026 db/conf/aaai/aaai2026.html#LuoCHH26

Wen Luo Peng Chen Xiaotao Huang LiQun Huang ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning. 2026 January abs/2601.17818 CoRR https://doi.org/10.48550/arXiv.2601.17818 db/journals/corr/corr2601.html#abs-2601-17818 streams/journals/corr

Peng Chen Xiaotao Huang Wen Luo