@inproceedings{wu-etal-2026-union,
title = "Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers",
author = "Wu, Songhao and
Lv, Ang and
Xie, Ruobing and
Sun, Samm and
Wang, Di and
Yan, Rui and
Lin, Yankai",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1675/",
pages = "36193--36206",
ISBN = "979-8-89176-390-6",
abstract = "Mixture-of-Experts (MoE) models rely on an external router to assign tokens to experts. This design inherently separates the routing decision from each expert{'}s internal capabilities, leading to suboptimal performance. In this work, we address this limitation with Union-of-Experts (UoE), an MoE variant that performs ``expert-autonomous routing''. The core mechanism of UoE is to pre-designate a minute fraction of neurons within each expert as ``routing neurons''. Experts autonomously select relevant tokens by comparing the activation intensity of these neurons, aligning routing decisions with each expert{'}s functional profile. To prevent the waste of activations from unselected experts' routing neurons, we aggregate all routing neuron outputs and sum them into the final layer output. This aggregation acts as a novel virtual shared expert whose parameters are distributed across the individual experts, and improves overall parameter efficiency. We pre-train UoE models with up to 3B parameters, demonstrating that they outperform traditional MoEs with matched efficiency. Furthermore, our analysis of the routing neurons provides valuable insights into expert-autonomous selection and the broader routing mechanisms of MoE models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2026-union">
<titleInfo>
<title>Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Songhao</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ang</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruobing</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samm</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yankai</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Mixture-of-Experts (MoE) models rely on an external router to assign tokens to experts. This design inherently separates the routing decision from each expert’s internal capabilities, leading to suboptimal performance. In this work, we address this limitation with Union-of-Experts (UoE), an MoE variant that performs “expert-autonomous routing”. The core mechanism of UoE is to pre-designate a minute fraction of neurons within each expert as “routing neurons”. Experts autonomously select relevant tokens by comparing the activation intensity of these neurons, aligning routing decisions with each expert’s functional profile. To prevent the waste of activations from unselected experts’ routing neurons, we aggregate all routing neuron outputs and sum them into the final layer output. This aggregation acts as a novel virtual shared expert whose parameters are distributed across the individual experts, and improves overall parameter efficiency. We pre-train UoE models with up to 3B parameters, demonstrating that they outperform traditional MoEs with matched efficiency. Furthermore, our analysis of the routing neurons provides valuable insights into expert-autonomous selection and the broader routing mechanisms of MoE models.</abstract>
<identifier type="citekey">wu-etal-2026-union</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1675/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>36193</start>
<end>36206</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers
%A Wu, Songhao
%A Lv, Ang
%A Xie, Ruobing
%A Sun, Samm
%A Wang, Di
%A Yan, Rui
%A Lin, Yankai
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F wu-etal-2026-union
%X Mixture-of-Experts (MoE) models rely on an external router to assign tokens to experts. This design inherently separates the routing decision from each expert’s internal capabilities, leading to suboptimal performance. In this work, we address this limitation with Union-of-Experts (UoE), an MoE variant that performs “expert-autonomous routing”. The core mechanism of UoE is to pre-designate a minute fraction of neurons within each expert as “routing neurons”. Experts autonomously select relevant tokens by comparing the activation intensity of these neurons, aligning routing decisions with each expert’s functional profile. To prevent the waste of activations from unselected experts’ routing neurons, we aggregate all routing neuron outputs and sum them into the final layer output. This aggregation acts as a novel virtual shared expert whose parameters are distributed across the individual experts, and improves overall parameter efficiency. We pre-train UoE models with up to 3B parameters, demonstrating that they outperform traditional MoEs with matched efficiency. Furthermore, our analysis of the routing neurons provides valuable insights into expert-autonomous selection and the broader routing mechanisms of MoE models.
%U https://aclanthology.org/2026.acl-long.1675/
%P 36193-36206
Markdown (Informal)
[Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers](https://aclanthology.org/2026.acl-long.1675/) (Wu et al., ACL 2026)
ACL
- Songhao Wu, Ang Lv, Ruobing Xie, Samm Sun, Di Wang, Rui Yan, and Yankai Lin. 2026. Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 36193–36206, San Diego, California, United States. Association for Computational Linguistics.