@inproceedings{xiang-etal-2025-bcqlm,
title = "{B}c{QLM}: Efficient Vision-Language Understanding with Distilled {Q}-Gated Cross-Modal Fusion",
author = "Xiang, Sike and
Chen, Shuang and
Atapour-Abarghouei, Amir",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.780/",
pages = "14462--14472",
ISBN = "979-8-89176-335-7",
abstract = "As multimodal large language models (MLLMs) advance, their large-scale architectures pose challenges for deployment in resource-constrained environments. In the age of large models, where energy efficiency, computational scalability and environmental sustainability are paramount, the development of lightweight and high-performance models is critical for real-world applications. As such, we propose a lightweight MLLM framework for end-to-end visual question answering. Our proposed approach centres on BreezeCLIP, a compact yet powerful vision-language encoder optimised for efficient multimodal understanding. With only 1.2 billion parameters overall, our model significantly reduces computational cost while achieving performance comparable to standard-size MLLMs. Experiments conducted on multiple datasets further validate its effectiveness in balancing accuracy and efficiency. The modular and extensible design enables generalisation to broader multimodal tasks. The proposed lightweight vision-language framework is denoted as BcQLM (BreezeCLIP-enhanced Q-Gated Multimodal Language Model). It offers a promising path toward deployable MLLMs under practical hardware constraints. The source code is available at \url{https://github.com/thico0224/BcQLM}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiang-etal-2025-bcqlm">
<titleInfo>
<title>BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sike</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Atapour-Abarghouei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>As multimodal large language models (MLLMs) advance, their large-scale architectures pose challenges for deployment in resource-constrained environments. In the age of large models, where energy efficiency, computational scalability and environmental sustainability are paramount, the development of lightweight and high-performance models is critical for real-world applications. As such, we propose a lightweight MLLM framework for end-to-end visual question answering. Our proposed approach centres on BreezeCLIP, a compact yet powerful vision-language encoder optimised for efficient multimodal understanding. With only 1.2 billion parameters overall, our model significantly reduces computational cost while achieving performance comparable to standard-size MLLMs. Experiments conducted on multiple datasets further validate its effectiveness in balancing accuracy and efficiency. The modular and extensible design enables generalisation to broader multimodal tasks. The proposed lightweight vision-language framework is denoted as BcQLM (BreezeCLIP-enhanced Q-Gated Multimodal Language Model). It offers a promising path toward deployable MLLMs under practical hardware constraints. The source code is available at https://github.com/thico0224/BcQLM.</abstract>
<identifier type="citekey">xiang-etal-2025-bcqlm</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.780/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>14462</start>
<end>14472</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion
%A Xiang, Sike
%A Chen, Shuang
%A Atapour-Abarghouei, Amir
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F xiang-etal-2025-bcqlm
%X As multimodal large language models (MLLMs) advance, their large-scale architectures pose challenges for deployment in resource-constrained environments. In the age of large models, where energy efficiency, computational scalability and environmental sustainability are paramount, the development of lightweight and high-performance models is critical for real-world applications. As such, we propose a lightweight MLLM framework for end-to-end visual question answering. Our proposed approach centres on BreezeCLIP, a compact yet powerful vision-language encoder optimised for efficient multimodal understanding. With only 1.2 billion parameters overall, our model significantly reduces computational cost while achieving performance comparable to standard-size MLLMs. Experiments conducted on multiple datasets further validate its effectiveness in balancing accuracy and efficiency. The modular and extensible design enables generalisation to broader multimodal tasks. The proposed lightweight vision-language framework is denoted as BcQLM (BreezeCLIP-enhanced Q-Gated Multimodal Language Model). It offers a promising path toward deployable MLLMs under practical hardware constraints. The source code is available at https://github.com/thico0224/BcQLM.
%U https://aclanthology.org/2025.findings-emnlp.780/
%P 14462-14472
Markdown (Informal)
[BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion](https://aclanthology.org/2025.findings-emnlp.780/) (Xiang et al., Findings 2025)
ACL