WANG, Chengcheng; HE, Haowen; ZHAO, Liang; DENG, Xiaoheng; DUAN, Lixin; WAN, Shaohua. CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 31, p. 26133–26141, 2026. DOI: 10.1609/aaai.v40i31.39816. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39816. Acesso em: 25 may. 2026.