@inproceedings{vuong-etal-2026-survey,
title = "A Survey on Knowledge Distillation of Vision-Language Models",
author = "Vuong, Hoang Tran and
Dao, Dat and
Chi, Pham Khanh and
Truong, Minh-Phuc and
Tran, Quyen and
Van, Linh Ngo and
Nguyen, Thien Huu and
Do, Thanh-Toan and
Le, Trung",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.180/",
pages = "3806--3846",
ISBN = "979-8-89176-462-0",
abstract = "Vision-language models (VLMs) achieve strong multimodal performance but remain expensive to deploy. Knowledge distillation (KD) is an effective approach for compressing these models and transferring their capabilities to more efficient student models. While KD for large language models (LLMs) is already well surveyed, no existing work provides systematic coverage of KD for VLMs, where the addition of a visual modality introduces challenges that text-only distillation does not face. This paper presents the first dedicated survey of knowledge distillation for vision-language models. We propose a unified taxonomy that organizes methods along three orthogonal views: knowledge type, teacher accessibility, and structural compatibility, and use it to organize methods across major VLM distillation settings. We also survey the associated datasets and evaluation protocols, identify open challenges and outline directions for future research. We further maintain a GitHub repository at https://github.com/HoangTran223/Awesome-Knowledge-Distillation-of-VLMs to compile all surveyed papers, which we will actively update."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vuong-etal-2026-survey">
<titleInfo>
<title>A Survey on Knowledge Distillation of Vision-Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hoang</namePart>
<namePart type="given">Tran</namePart>
<namePart type="family">Vuong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dat</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pham</namePart>
<namePart type="given">Khanh</namePart>
<namePart type="family">Chi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minh-Phuc</namePart>
<namePart type="family">Truong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quyen</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="given">Ngo</namePart>
<namePart type="family">Van</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thanh-Toan</namePart>
<namePart type="family">Do</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Vision-language models (VLMs) achieve strong multimodal performance but remain expensive to deploy. Knowledge distillation (KD) is an effective approach for compressing these models and transferring their capabilities to more efficient student models. While KD for large language models (LLMs) is already well surveyed, no existing work provides systematic coverage of KD for VLMs, where the addition of a visual modality introduces challenges that text-only distillation does not face. This paper presents the first dedicated survey of knowledge distillation for vision-language models. We propose a unified taxonomy that organizes methods along three orthogonal views: knowledge type, teacher accessibility, and structural compatibility, and use it to organize methods across major VLM distillation settings. We also survey the associated datasets and evaluation protocols, identify open challenges and outline directions for future research. We further maintain a GitHub repository at https://github.com/HoangTran223/Awesome-Knowledge-Distillation-of-VLMs to compile all surveyed papers, which we will actively update.</abstract>
<identifier type="citekey">vuong-etal-2026-survey</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.180/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3806</start>
<end>3846</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey on Knowledge Distillation of Vision-Language Models
%A Vuong, Hoang Tran
%A Dao, Dat
%A Chi, Pham Khanh
%A Truong, Minh-Phuc
%A Tran, Quyen
%A Van, Linh Ngo
%A Nguyen, Thien Huu
%A Do, Thanh-Toan
%A Le, Trung
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F vuong-etal-2026-survey
%X Vision-language models (VLMs) achieve strong multimodal performance but remain expensive to deploy. Knowledge distillation (KD) is an effective approach for compressing these models and transferring their capabilities to more efficient student models. While KD for large language models (LLMs) is already well surveyed, no existing work provides systematic coverage of KD for VLMs, where the addition of a visual modality introduces challenges that text-only distillation does not face. This paper presents the first dedicated survey of knowledge distillation for vision-language models. We propose a unified taxonomy that organizes methods along three orthogonal views: knowledge type, teacher accessibility, and structural compatibility, and use it to organize methods across major VLM distillation settings. We also survey the associated datasets and evaluation protocols, identify open challenges and outline directions for future research. We further maintain a GitHub repository at https://github.com/HoangTran223/Awesome-Knowledge-Distillation-of-VLMs to compile all surveyed papers, which we will actively update.
%U https://aclanthology.org/2026.findings-emnlp.180/
%P 3806-3846
Markdown (Informal)
[A Survey on Knowledge Distillation of Vision-Language Models](https://aclanthology.org/2026.findings-emnlp.180/) (Vuong et al., Findings 2026)
ACL
- Hoang Tran Vuong, Dat Dao, Pham Khanh Chi, Minh-Phuc Truong, Quyen Tran, Linh Ngo Van, Thien Huu Nguyen, Thanh-Toan Do, and Trung Le. 2026. A Survey on Knowledge Distillation of Vision-Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 3806–3846, Budapest, Hungary. Association for Computational Linguistics.