TC-MoE: Augmenting Mixture of Experts with Ternary Expert Choice.
Shen Yan, Xingyan Bin, Sijun Zhang, Yisen Wang, Zhouchen Lin
Browse the full ICLR paper archive.
Shen Yan, Xingyan Bin, Sijun Zhang, Yisen Wang, Zhouchen Lin
Browse the full ICLR paper archive.