Zhuang, Jiedong, Lu Lu, Ming Dai, Rui Hu, Jian Chen, Qiang Liu, and Haoji Hu. “ST3: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming”. Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 10 (April 11, 2025): 11049–11057. Accessed May 11, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/33201.