Chain-of-Experts replaces one parallel MoE routing step with several sequential expert steps inside a layer, reporting lower loss and memory use in small-scale experiments.
Mixture-of-experts with expert choice routing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Chain-of-Experts: Unlocking the Communication Power of Mixture-of-Experts Models
Chain-of-Experts replaces one parallel MoE routing step with several sequential expert steps inside a layer, reporting lower loss and memory use in small-scale experiments.