Rethinking Routing Exploration in Modern Mixture-of-Experts
MirrorMoE fixes MoE routing under-exploration from shared experts by suppressing unneeded experts per token.
1 stories, newest first · one card per story
MirrorMoE fixes MoE routing under-exploration from shared experts by suppressing unneeded experts per token.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views