MA, Yinchao; ZHOU, Qiang; WANG, Zhibin; CHEN, Xianing; YANG, Hanqing; SONG, Jun; ZHENG, Bo. Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 29, p. 24317–24325, 2026. DOI: 10.1609/aaai.v40i29.39612. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39612. Acesso em: 27 may. 2026.