AcceptMoE is a verifier-side expert selector that uses commitment-weighted router demand and an entropy-based set size, reducing expert traffic while keeping mean accuracy within 0.27 percentage points of EAGLE-3 with natural routing.
Proceedings of the 41st International Conference on Machine Learning , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decoding
AcceptMoE is a verifier-side expert selector that uses commitment-weighted router demand and an entropy-based set size, reducing expert traffic while keeping mean accuracy within 0.27 percentage points of EAGLE-3 with natural routing.