---
title: README
emoji: 🌍
colorFrom: pink
colorTo: green
sdk: static
pinned: false
---

# VLM2Vec & MMEB: Benchmarking multimodal embeddings and adapting state-of-the-art multimodal large language models into embedding models.

- **Website** - https://tiger-ai-lab.github.io/VLM2Vec/

- **Github** https://github.com/TIGER-AI-Lab/VLM2Vec


## List of Our Papers

### Main VLM2Vec / MMEB Series
- **[VLM2Vec / MMEB](https://arxiv.org/pdf/2410.05160)** – Image embedding benchmarking and models.  (ICLR2025)
- **[VLM2Vec-V2 / MMEB-V2](https://arxiv.org/pdf/2507.04590)** – Extension of our previous work to video and visual document tasks.  (TMLR2026) 

### Other Related Papers from Our Team
- **[GAE-Retriever](https://arxiv.org/pdf/2506.22056)** – Benchmark and model for trajectory modeling in GUI environments.  (Computer-use Agents@ICML 2025)
- **[B3](https://arxiv.org/pdf/2505.11293)** – A novel batch mining strategy for contrastive learning.  (Neurips2025)