Skip to content

CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices.

Chengcheng Wang, Haowen He, Liang Zhao, Xiaoheng Deng, Lixin Duan, Shaohua Wan

VenueA*AAAI
Year2026
ProceedingsAAAI

Browse the full AAAI paper archive.