2026-06-26 04:00 UTCOriginal source2 min readUpdated: 2026-06-26 08:09 UTC

GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models

GeMoE models token routing as a Minimum Description Length problem, using gating entropy to adaptively select experts, achieving 99.5% performance retention while increasing expert activation sparsity by 36.5%.

SourcearXiv Computer VisionAuthor: Chaoxiang Cai, Minghe Weng, Jie Li, Yibo Jiang, Longrong Yang, Zequn Qin, Xi Li

[2606.26287] GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models

[Submitted on 24 Jun 2026]

Title:GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models

View a PDF of the paper titled GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models, by Chaoxiang Cai and 5 other authors

View PDF HTML (experimental)

Abstract:With the increase in model parameters and training data, the instruction following and generalization capabilities of Large VisionLanguage Models (LVLMs) have been significantly improved. Based on the Mixture of Experts (MoE) architecture, LVLMs expand their parameter capacity while maintaining the inference cost. However, traditional MoE methods employ a Top-k static routing strategy, which fails to account for variations in the input and adaptively select the number of experts, resulting in suboptimal resource utilization. In this paper, we propose viewing token routing as an information encoding task, framing dynamic routing as a Minimum Description Length (MDL) problem in encoding By validating the connection between MDL and gating entropy in the MoE scenario, we introduce Gating Entropy-based Uncertainty-aware Adaptive Routing (GeMoE) for MoE. Unlike traditional static or heuristic-based dynamic routing methods, GeMoE explicitly models the trade-off between model complexity and performance. By using gating entropy to assess the complexity of tokens, GeMoE adaptively determines the number of experts each token should engage. On a wide range of backbones and benchmarks, our method achieves 99.5% average performance retention compared to the original static routing, while improving average expert activation sparsity by 36.5%.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2606.26287 [cs.CV]

(or arXiv:2606.26287v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.26287

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xi Li [view email] [v1] Wed, 24 Jun 2026 18:34:00 UTC (2,307 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models, by Chaoxiang Cai and 5 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-06

Change to browse by:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

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

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)