aihao2000/DPN-LLaVA

Arxiv 25: Dynamic Pyramid Network for Efficient Multimodal Large Language Model

41
/ 100
Emerging

This project helps developers working with Multimodal Large Language Models (MLLMs) to make them run more efficiently. It takes an existing MLLM and image data, processing them to produce a faster MLLM that maintains its ability to understand fine-grained visual details. AI/ML engineers and researchers who are building or deploying MLLMs will find this useful.

Use this if you need to reduce the computational cost and improve the inference speed of your Multimodal Large Language Models without significantly sacrificing their detailed image understanding capabilities.

Not ideal if you are not working with Multimodal Large Language Models or if your primary concern is not model efficiency.

AI/ML engineering Multimodal AI Large Language Models Model optimization Computer vision
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

44

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Dec 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/aihao2000/DPN-LLaVA"

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