@inproceedings{song-etal-2026-brainmoe,
title = "{B}rain{M}o{E}: A Brain-Inspired Modular Mixture-of-Experts Model for Multimodal Reasoning",
author = "Song, Siyao and
Zhang, Yunhao and
Sun, Jingyuan and
Zhang, Yaping and
Zong, Chengqing",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.271/",
pages = "6004--6022",
ISBN = "979-8-89176-439-2",
abstract = "Reliable cross-modal reasoning requires Multimodal Large Language Model (MLLMs) with interpretable and controllable computation. However, existing models rely on data-driven architectures that entangle multimodal processing, obscuring the functional processes underlying their outputs. Inspired by the human brain{'}s specialized and dynamically collaborative networks, we propose **BrainMoE**, a multimodal MoE model with six sensory and cognitive experts: Language, Logic, Social, World Knowledge, Vision, and Auditory. To support flexible sensory{--}cognitive coordination, we incorporates a layer-wise adaptive router that dynamically determines which experts are activated at each layer based on task-processing demands. Experiments on text, image, and audio reasoning benchmarks demonstrate that BrainMoE outperforms strong baselines by 1.59 and 2.2 points on text-only and multimodal benchmarks, while matching competitive external multimodal models. Routing and ablation analyses demonstrate clear expert specialization and causally important module-level contributions. Experiments on the cognitive benchmark further show that adaptive-routing BrainMoE aligns more closely with human behavioral patterns than baselines and static routing methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2026-brainmoe">
<titleInfo>
<title>BrainMoE: A Brain-Inspired Modular Mixture-of-Experts Model for Multimodal Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siyao</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunhao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingyuan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaping</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Reliable cross-modal reasoning requires Multimodal Large Language Model (MLLMs) with interpretable and controllable computation. However, existing models rely on data-driven architectures that entangle multimodal processing, obscuring the functional processes underlying their outputs. Inspired by the human brain’s specialized and dynamically collaborative networks, we propose **BrainMoE**, a multimodal MoE model with six sensory and cognitive experts: Language, Logic, Social, World Knowledge, Vision, and Auditory. To support flexible sensory–cognitive coordination, we incorporates a layer-wise adaptive router that dynamically determines which experts are activated at each layer based on task-processing demands. Experiments on text, image, and audio reasoning benchmarks demonstrate that BrainMoE outperforms strong baselines by 1.59 and 2.2 points on text-only and multimodal benchmarks, while matching competitive external multimodal models. Routing and ablation analyses demonstrate clear expert specialization and causally important module-level contributions. Experiments on the cognitive benchmark further show that adaptive-routing BrainMoE aligns more closely with human behavioral patterns than baselines and static routing methods.</abstract>
<identifier type="citekey">song-etal-2026-brainmoe</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.271/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>6004</start>
<end>6022</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BrainMoE: A Brain-Inspired Modular Mixture-of-Experts Model for Multimodal Reasoning
%A Song, Siyao
%A Zhang, Yunhao
%A Sun, Jingyuan
%A Zhang, Yaping
%A Zong, Chengqing
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F song-etal-2026-brainmoe
%X Reliable cross-modal reasoning requires Multimodal Large Language Model (MLLMs) with interpretable and controllable computation. However, existing models rely on data-driven architectures that entangle multimodal processing, obscuring the functional processes underlying their outputs. Inspired by the human brain’s specialized and dynamically collaborative networks, we propose **BrainMoE**, a multimodal MoE model with six sensory and cognitive experts: Language, Logic, Social, World Knowledge, Vision, and Auditory. To support flexible sensory–cognitive coordination, we incorporates a layer-wise adaptive router that dynamically determines which experts are activated at each layer based on task-processing demands. Experiments on text, image, and audio reasoning benchmarks demonstrate that BrainMoE outperforms strong baselines by 1.59 and 2.2 points on text-only and multimodal benchmarks, while matching competitive external multimodal models. Routing and ablation analyses demonstrate clear expert specialization and causally important module-level contributions. Experiments on the cognitive benchmark further show that adaptive-routing BrainMoE aligns more closely with human behavioral patterns than baselines and static routing methods.
%U https://aclanthology.org/2026.aacl-long.271/
%P 6004-6022
Markdown (Informal)
[BrainMoE: A Brain-Inspired Modular Mixture-of-Experts Model for Multimodal Reasoning](https://aclanthology.org/2026.aacl-long.271/) (Song et al., AACL-IJCNLP 2026)
ACL
- Siyao Song, Yunhao Zhang, Jingyuan Sun, Yaping Zhang, and Chengqing Zong. 2026. BrainMoE: A Brain-Inspired Modular Mixture-of-Experts Model for Multimodal Reasoning. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6004–6022, Hengqin, China. Association for Computational Linguistics.