baaivision/EVE

EVE Series: Encoder-Free Vision-Language Models from BAAI

38
/ 100
Emerging

EVE provides advanced research in Vision-Language Models (VLMs) by exploring methods to remove the traditional vision encoder. It takes image data and text as input and aims to produce highly capable multimodal AI models. This project is for AI researchers and practitioners focused on developing or understanding next-generation vision-language AI.

368 stars. No commits in the last 6 months.

Use this if you are an AI researcher investigating novel architectures for multimodal large language models, specifically interested in encoder-free designs.

Not ideal if you are a business user looking for a ready-to-deploy tool or an application developer seeking a stable API for immediate integration into a product.

AI-research vision-language-models deep-learning multimodal-AI computational-linguistics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

368

Forks

12

Language

Python

License

MIT

Last pushed

Jul 24, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/baaivision/EVE"

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