1.
Wang C, He H, Zhao L, Deng X, Duan L, Wan S. CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 25];40(31):26133-41. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/39816