Wang H, Xie W, Jiang H, Wei Y, Jiang K, Cao M, et al. TOP-RL: Task-Optimized Progressive Token Pruning with Reinforcement Learning for Vision Language Models. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 13];40(18):15824-32. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/38614