Is ST-MoE superseded?

ST-MoE (Mixture-of-experts routing): superseded — cited as a baseline and beaten by newer methods. 0 paper(s) critique it, 2 beat it on benchmarks — #90 of 1370 most-superseded. Sub-problem: cluster led by MoE-LLaVA. Newer alternatives in the same sub-problem include MoE-GRPO, Input Domain Aware MoE.

Mixture-of-experts routing

ST-MoE

ST-MoE: Designing Stable and Transferable Sparse Expert Models

Superseded baseline#90 of 1,370 most-superseded · first seen Feb 17, 2022

Superseded — cited as a baseline and beaten by newer methods

0 papers critique it · 2 beat it on benchmarks

Beaten on benchmarks

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

IDA-MoE beats ST-MoE
43.1 vs 38.2
VizWiz · [StableLM-1.6B + CLIP-336]
Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts
Hi-MoE beats ST-MoE
2.947 vs 2.981
PPL · [nanoGPT on OpenWebText]
Hierarchical Mixture-of-Experts with Two-Stage Optimization

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

MoE-GRPOMoE-GRPO: Optimizing Mixture-of-Experts via Reinforcement Learning in Vision-Language Models
Mar 26, 2026
Input Domain Aware MoEInput Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts
Oct 18, 2025