Li Y, Yang J, Shen Z, Han L, Xu H, Tang R. CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning. AAAI [Internet]. 2026Mar.14 [cited 2026May4];40(8):6619-27. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/37592