Wang, C., He, H., Zhao, L., Deng, X., Duan, L., & Wan, S. (2026). CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices. Proceedings of the AAAI Conference on Artificial Intelligence, 40(31), 26133–26141. https://doi.org/10.1609/aaai.v40i31.39816