VLM2Vec
This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]
Evaluate and compare different models that understand and retrieve information from text, images, and audio.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeThis repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]
VLM2Vec has 666 stars on GitHub. It has been forked 62 times. VLM2Vec is written mainly in Python. It has been in active development since 2024. VLM2Vec is available under the Apache-2.0 license. Its main topics are benchmark, contrastive-learning, embedding, image-retrieval.
What is VLM2Vec?
This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]
Is VLM2Vec open source?
VLM2Vec is an open-source project. It is released under the Apache-2.0 license.
Is VLM2Vec free?
Yes. VLM2Vec is free and open source — you can use, modify and self-host it.
What license does VLM2Vec use?
VLM2Vec is available under the Apache-2.0 license.
What language is VLM2Vec written in?
VLM2Vec is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/tiger-ai-lab-vlm2vec.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.