AI Paper Atlas

Research map / Architectures and efficiency / Mixture of experts

SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models

Juntong Wu, Jialiang Cheng, Fuyu Lv, OU Dan, Li Yuan

ICLR 2026 · Architectures and efficiency › Mixture of experts · approach: Expert routing and specialization · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
re-route to most similar expert instead of a random expert (ablation)SERE · Re-routing target ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 41.68 -> 47.15Improved
re-route to most similar expert instead of the least similar expert (ablation)SERE · Re-routing target ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 28.74 -> 47.15Improved
re-route to most similar expert instead of a random expert (ablation)SERE · Re-routing target ablation, top-1 (Qwen1.5-MoE-A2.7B)average accuracy: 27.74 -> 37.87Improved
re-route to most similar expert instead of the least similar expert (ablation)SERE · Re-routing target ablation, top-1 (Qwen1.5-MoE-A2.7B)average accuracy: 4.72 -> 37.87Improved
use Frobenius instead of cosine similarity for the expert similarity matrix (ablation)SERE · Similarity metric ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 45.55 -> 47.15Improved
use Frobenius instead of CKA-RBF similarity (ablation)SERE · Similarity metric ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 46.85 -> 47.15No clear effect
use activation-based similarity instead of data-free parameter-based (Concat, Frobenius) similarity (ablation)SERE · Similarity matrix ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 45.14 -> 47.15Improved
use activation-based similarity instead of data-free parameter-based (Logic, Frobenius) similarity (ablation)SERE · Similarity matrix ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 44.26 -> 47.15Improved
calibrate with C4 instead of FineWeb-Edu (ablation)SERE · Calibration dataset ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 47.15 -> 47.09No clear effect
calibrate with domain-specific Exam data instead of FineWeb-Edu at K=1 (ablation)SERE · Calibration dataset ablation, top-1 (Qwen1.5-MoE-A2.7B)average accuracy: 37.87 -> 38.14Improved
increase calibration volume from 200x64 to 800x256 tokens (FineWeb, K=2) (ablation)SERE · Calibration volume ablation, top-2 (Qwen1.5-MoE-A2.7B)average accuracy: 46.66 -> 46.58No clear effect
add critical-expert preservation (rho=0.3) to SERE top-1 (ablation)SERE · OpenCompass average (Qwen1.5-MoE-A2.7B)average accuracy: 37.87 -> 39.82Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy