HAN, Yuhang; LIU, Xuyang; ZHANG, Zihan; DING, Pengxiang; CHEN, Junjie; CHEN, Honggang; WANG, Donglin; YAN, Qingsen; HUANG, Siteng. Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 6, p. 4601–4609, 2026. DOI: 10.1609/aaai.v40i6.42460. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/42460. Acesso em: 17 may. 2026.