Han Y, Liu X, Zhang Z, Ding P, Chen J, Chen H, et al. Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 17];40(6):4601-9. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/42460