arXiv Computation and Language September 2, 2026 By Ziyan Gan, Fangxin Liu, Chenyang Guan, Junjie Wang, Ning Yang, Haomin Li, Xiang Li, Siran Yang, Jiamang Wang, Lin Qu, Zongwu Wang, Li Jiang, Haibing Guan

PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition

Read the original on arXiv Computation and Language →

PCoMoE introduces a path‑compositional execution framework that moves Mixture‑of‑Experts inference from coarse‑grained expert selection to fine‑grained path composition. It uses a path‑level formulation of expert computation, a compatibility‑aware layer‑wise pruning strategy to eliminate low‑value path combinations, and a hardware‑friendly execution engine that reuses sub‑expert structures with bounded overhead. Experiments show up to a 1.31× speedup and a 10% accuracy improvement over existing MoE inference methods.

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 Computation and Language.

Hugging Face Trending Papers

Sep 1

PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition

Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remains heavily constrain...

llms efficiency

arXiv Machine Learning

Jun 17

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models

arXiv:2602. 06154v2 Announce Type: replace Abstract: Mixture-of-Experts (MoE) models scale large language models efficiently by sparsely activating experts, but once an expert is selected, it is executed fully.

By Nurbek Tastan, Stefanos Laskaridis, Karthik Nandakumar, Samuel Horvath

llms benchmarks

arXiv AI

Jun 2

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

arXiv:2606. 01062v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performance remains a challenge.

By Jiarui Feng, Hanqing Zeng, Karish Grover, Ruizhong Qiu, Yinglong Xia, Qiang Zhang, Qifan Wang, Ren Chen, Dongqi Fu, Jiayi Liu, Zhoukai Zhao, Xiangjun Fan, Benyu Zhang, Yixin Chen

llms fine-tuning

arXiv Machine Learning

Jun 16

A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference

arXiv:2606. 15453v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based large language models (LLMs), such as Qwen and DeepSeek, have recently emerged as an effective approach to improving model capacity without proportionally increasing computational cost.

By Yingnan Zhao, Razvan Bunescu, Ahmed Louri, Avinash Karanth, Ke Wang

llms

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 AI

Jul 7

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference

arXiv:2511. 04805v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models have shown strong potential in scaling language models efficiently by activating only a small subset of experts per input.

By Yushu Zhao, Zheng Wang, Minjia Zhang

llms benchmarks

One email a morning, machine-written

Related stories

PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition

MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language Models

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference

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

PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert Merging and Bit-packed inference