arXiv AI September 7, 2026 By Zukang Xu, Zhixiong Zhao, Xing Hu, Jiangyong Yu, Houji Wen, Jun Li, Zhe Jiang, Dawei Yang

ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs

ACE introduces a training‑free, calibration‑free framework for adaptive expert skipping in Mixture‑of‑Experts LLMs. It combines a Global Spectral Proxy that estimates global transformation capacity with a Router‑Conditioned Refinement that builds expert‑specific direction prototypes, enabling the model to skip low‑contribution experts while always keeping the top‑1 expert. Offline computation of expert statistics leaves only lightweight table lookups during inference, and experiments on three MoE‑based LLMs show ACE outperforms static and dynamic baselines, especially at high skipping ratios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 27

Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing

The paper introduces Ban&Pick, a post‑training, plug‑and‑play routing strategy for Sparse Mixture‑of‑Experts large language models. It identifies and reinforces a small group of highly influential experts while dynamically pruning redundant ones, leading to accuracy gains across math, code, and reasoning benchmarks. Experiments on DeepSeek and Qwen3 show notable performance improvements and a 1.25× inference speedup without retraining or architectural changes.

By Yuanteng Chen, Peisong Wang, Yuantian Shao, Nanxin Zeng, Chang Xu, Jian Cheng

llms benchmarks

arXiv Machine Learning

Sep 30

BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding

arXiv:2609.36222v1 Announce Type: new Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferrin...

By Ali Abbasi, Justin Shi, Soheil Kolouri

llms efficiency

arXiv Machine Learning

Aug 12

Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation

arXiv:2608. 10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.

By Gongli Zhang, Zhulin Liu, C. L. Philip Chen

rag efficiency

arXiv Machine Learning

Aug 11

Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-Experts

arXiv:2608. 08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs.

By Zongfei Li

arXiv AI

Jul 13

Sticky Routing: Training MoE Models for Memory-Efficient Inference

arXiv:2607. 08780v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models activate only a sparse subset of experts per token, yet consecutive tokens frequently activate different experts -- causing constant weight swapping between slow storage and fast memory on edge devices.

By Ali Kayyam

llms fine-tuning

Hugging Face Trending Papers

Aug 5

Elbow-Based MoE Routing: A Training-Free Inference Time Plugin for Expert Selection

Mixture-of-Experts (MoE) models enable model scaling while maintaining low inference-time compute by activating only a subset of experts per token. However, conventional routing relies on a fixed top-k selection, forcing the model to spend the same compute regardless of how many experts are relevant.

benchmarks

One email a morning, machine-written

Related stories

Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing

BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding

Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation

Beyond Routing: Decoupling Expert Dispatch and Aggregation in Sparse Mixture-of-Experts

Sticky Routing: Training MoE Models for Memory-Efficient Inference

Elbow-Based MoE Routing: A Training-Free Inference Time Plugin for Expert Selection