Wang, Chengcheng, Haowen He, Liang Zhao, Xiaoheng Deng, Lixin Duan, and Shaohua Wan. “CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-Constrained Devices”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 31 (March 14, 2026): 26133–26141. Accessed May 25, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/39816.