CMoE (Mixture-of-experts routing): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 1 beat it on benchmarks — #104 of 1370 most-superseded. Sub-problem: cluster led by LLaMA-MoE. Newer alternatives in the same sub-problem include DOT-MoE, ZEDA, ExpertWeaver, Mixture-of-Experts (MoE) Adaptation, Elastic Mixture-of-Experts (EMoE).

Mixture-of-experts routing

CMoE

CMoE: Converting Mixture-of-Experts from Dense to Accelerate LLM Inference

Superseded baseline#104 of 1,370 most-superseded · first seen Feb 6, 2025

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 1 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites CMoE as a baseline.

Unlike existing methods cmoe, llamamoe, llamamoev2 which freeze the assignment and then train the router, DOT-MoE allows the router and the expert assignment to co-adapt.

— DOT-MoE: Differentiable Optimal Transport for MoEfication

Beaten on benchmarks

Head-to-head results where a newer method reports beating CMoE. Values are copied from the source paper's tables — verify against the cited paper.

ExpertWeaver beats CMoE
60.4 vs 57.2
Avg. · [LLaMA3-8B, 25% sparsity]
ExpertWeaver: Unlocking the Inherent MoE in Dense LLMs with GLU Activation Patterns

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.