Jiang, Hao, Yang Jin, Zhicheng Sun, Kun Xu, Kun Xu, Liwei Chen, Yang Song, Kun Gai, and Yadong Mu. “Granularity-Adaptive Spatial Evidence Tokenization for Video Question Answering”. Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 4 (April 11, 2025): 3976-3984. Accessed April 27, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/32416.