swordlidev/Efficient-Multimodal-LLMs-Survey

Efficient Multimodal Large Language Models: A Survey

40
/ 100
Emerging

This is a survey for researchers and engineers working with multimodal large language models (MLLMs). It provides a comprehensive overview of efficient MLLMs, outlining their architectures, strategies for efficiency, and real-world applications. The resource takes in the latest research papers and categorizes them, allowing practitioners to understand the current landscape, limitations, and future directions of MLLM development, particularly for resource-constrained environments.

389 stars. No commits in the last 6 months.

Use this if you need to understand the current state-of-the-art in efficient Multimodal Large Language Models, especially for deploying them in scenarios like edge computing.

Not ideal if you are looking for an off-the-shelf, ready-to-use MLLM solution or a coding tutorial.

AI-research machine-learning-engineering model-optimization edge-AI computer-vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

389

Forks

21

Language

License

Apache-2.0

Last pushed

Apr 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/swordlidev/Efficient-Multimodal-LLMs-Survey"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.