Luo, W., P. Chen, X. Huang, and L. Huang. “ViTCoP: Accelerating Large Vision-Language Models via Visual and Textual Semantic Collaborative Pruning”. Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, no. 29, Mar. 2026, pp. 24151-9, doi:10.1609/aaai.v40i29.39594.