L2R (Mixture-of-experts routing): current frontier — recent, not yet superseded in the knowledge base. 0 paper(s) critique it, 0 beat it on benchmarks — not ranked as a superseded baseline. Sub-problem: cluster led by Switch Transformer. Newer alternatives in the same sub-problem include ConceptM³oE, DisagMoE, Piper, GRACE-MoE, ReaLB.

Mixture-of-experts routing

L2R

L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts

On the frontierfirst seen Jan 29, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.

ConceptM³oEConceptM$^3$oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology
May 23, 2026
DisagMoEDisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism
May 10, 2026
PiperPiper: Efficient Large-Scale MoE Training via Resource Modeling and Pipelined Hybrid Parallelism
May 6, 2026
GRACE-MoEGRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference
May 6, 2026
ReaLBReaLB: Real-Time Load Balancing for Multimodal MoE Inference
Apr 21, 2026
LAER-MoELAER-MoE: Load-Adaptive Expert Re-layout for Efficient Mixture-of-Experts Training
Feb 12, 2026
Multi-Head LatentMoE and Head Parallel (HP)Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE Parallelism
Feb 4, 2026
L2RL2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts
Jan 29, 2026
Rasterized Steered Mixture of ExpertsRasterized Steered Mixture of Experts for Efficient 2D Image Regression
Oct 7, 2025
TanbrFaster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference
Sep 24, 2025