Feng, Ze, Sen Yang, Boqiang Duan, Wankou Yang, and Jingdong Wang. 2026. “EM-KD: Distilling Efficient Multimodal Large Language Model With Unbalanced Vision Tokens”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (25):21111-19. https://doi.org/10.1609/aaai.v40i25.39254.