Gao J, Qiao Q, Wu T, Wang Z, Cao Z, Li W. AIM: Let Any Multimodal Large Language Models Embrace Efficient In-Context Learning. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 13];39(3):3077-85. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/32316