大模型
arxiv.org ·
通过 L0 正则化混合专家加速稠密 LLM
论文提出 L0-MoE，一种基于 L0 正则化的轻量级混合专家方法，用于在几乎不损失性能的前提下加速稠密 LLM。方法引入聚类混淆矩阵进行领域感知的数据集构建，并采用动态批处理提升训练效率。实验称相比稠密模型最高获得 2.5 倍加速，同时保持有竞争力的性能，并优于现有 LLM 加速基线。
AI推荐理由 arXiv 论文摘要，提出 L0-MoE：用 L0 正则化把稠密 LLM 转为轻量 MoE，并引入聚类混淆矩阵做领域感知数据筛选、动态批处理训练；摘要称最高 2.5 倍加速且性能接近。信息密度较高、来源为论文原文，但仅有摘要级证据，未提供基准细节、模型规模和复现材料，加速与性能结论需以全文实验为准。
72
正文
Computer Science > Artificial Intelligence
arXiv:2609.21672 (cs)
[Submitted on 18 Sep 2026]
Title:Accelerating Dense LLMs via L0-regularized Mixture-of-Experts
Authors:Zhenyu Zhang, Jiudong Yang, Zhaowen Tao, Meng Chen
View a PDF of the paper titled Accelerating Dense LLMs via L0-regularized Mixture-of-Experts, by Zhenyu Zhang and 3 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeable performance degradation, while Mixture-of-Experts (MoE) models require extensive computational resources. In this paper, we propose L0-MoE, a lightweight MoE approach using L0-regularization to accelerate dense LLMs nearly without performance loss. Our method introduces a cluster confusion matrix for domain-aware dataset curation and applies dynamic batching for efficient training. Experiments show that L0-MoE achieves up to 2.5x speedup over dense models while maintaining competitive performance, outperforming existing LLM acceleration baselines.
Subjects:
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
Cite as:
arXiv:2609.21672 [cs.AI]
(or
arXiv:2609.21672v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.21672
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Journal reference:
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics, 2025
Submission history
From: Zhenyu Zhang [view email]
[v1]
Fri, 18 Sep 2026 12:08:31 UTC (240 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Accelerating Dense LLMs via L0-regularized Mixture-of-Experts, by Zhenyu Zhang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
cs.CL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)