Yxxxb/VoCo-LLaMA
[CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
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.
Stars
203
Forks
11
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
TinyLLaVA/TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
zjunlp/EasyInstruct
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
rese1f/MovieChat
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
NVlabs/Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies