Yxxxb/VoCo-LLaMA

[CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".

38
/ 100
Emerging

This project helps researchers and developers who work with large language models to process visual data more efficiently. It takes hundreds of visual data inputs, like image sequences from videos, and compresses them into a single, compact "VoCo token." This allows existing large language models to understand and interpret visual information without being overwhelmed by its size, making it suitable for those building advanced vision-language systems.

203 stars. No commits in the last 6 months.

Use this if you are a researcher or developer aiming to integrate large visual datasets into large language models while significantly reducing computational overhead.

Not ideal if you need a user-friendly tool for general image compression or video editing for non-technical purposes.

vision-language-models visual-ai-research machine-learning-engineering video-understanding model-optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

203

Forks

11

Language

Python

License

Apache-2.0

Last pushed

Jun 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Yxxxb/VoCo-LLaMA"

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