Feng Z, Yang S, Duan B, Yang W, Wang J. EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 13];40(25):21111-9. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39254