A Survey on Efficient Vision-Language Models

Gaurav Shinde, Anuradha Ravi, Emon Dey, Shadman Sakib, Milind Rampure +1 more
4/13/2025
cs.CV

No official code found. Best implementation: jingyi0000/VLM_survey (3,127 stars, last commit 2025-10-14). 1 more below.

Abstract

Vision-language models (VLMs) integrate visual and textual information, enabling a wide range of applications such as image captioning and visual question answering, making them crucial for modern AI systems. However, their high computational demands pose challenges for real-time applications. This has led to a growing focus on developing efficient vision language models. In this survey, we review key techniques for optimizing VLMs on edge and resource-constrained devices. We also explore compact VLM architectures, frameworks and provide detailed insights into the performance-memory trade-offs of efficient VLMs. Furthermore, we establish a GitHub repository at https://github.com/MPSCUMBC/Efficient-Vision-Language-Models-A-Survey to compile all surveyed papers, which we will actively update. Our objective is to foster deeper research in this area.

View on arXivView PDF

Code Implementations(2)

MPSC-UMBC/Efficient-Vision-Language-Models-A-SurveyCommunity100%

[2025] Efficient Vision Language Models: A Survey

523Feb 17, 20251 years ago
jingyi0000/VLM_surveyCommunity75%

Collection of AWESOME vision-language models for vision tasks

3,127233Mar 30, 20231 years ago
clipcomputer-visiondeep-learningknowledge-distillationmulti-modal-model+3 more

Similar Papers

MobileVLM V2: Faster and Stronger Baseline for Vision Language Model

89% match1 repo1.4k2024

Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts

89% match1 repo132025

Building and better understanding vision-language models: insights and future directions

89% match2024

Visual Large Language Models for Generalized and Specialized Applications

89% match1 repo2182025

POINTS: Improving Your Vision-language Model with Affordable Strategies

89% match2024

MOVE: A Mixture-of-Vision-Encoders Approach for Domain-Focused Vision-Language Processing

88% match2025

Cite this paper

@article{shinde2025survey,
  title  = {A Survey on Efficient Vision-Language Models},
  author = {Gaurav Shinde and Anuradha Ravi and Emon Dey and Shadman Sakib and Milind Rampure and Nirmalya Roy},
  year   = {2025},
  eprint = {2504.09724},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.09724v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.09724.svg)](https://codeofpaper.com/paper/2504.09724)

Discussion