V
VLM2Vec
TIGER-AI-Lab/VLM2Vec
This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]
★673stars
Python
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging benchmark and contrastive-learning, built with Python, open-source
Who made it?Maintained by TIGER-AI-Lab team, 673⭐ on GitHub, #1524 out of 3201 in Models
Why does it exist?As the Models landscape evolved, the TIGER-AI-Lab team identified the need for better benchmark solutions. VLM2Vec was created to simplify contrastive-learning workflows.
What can it do?Key use cases: embedding, image-retrieval, mmeb
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/TIGER-AI-Lab/VLM2Vec | 官网 https://tiger-ai-lab.github.io/VLM2Vec/
🔗 github.com/TIGER-AI-Lab/VLM2Vec | 官网 https://tiger-ai-lab.github.io/VLM2Vec/
Topics
benchmarkcontrastive-learningembeddingimage-retrievalmmebmultimodalragrepresentation-learningvideo-retrievalvisual-document-retrievalvlm