AIPython★ 704⑂ 66 forksApache-2.0
TIGER-AI-Lab/VLM2Vec
VLM2Vec: Vector Models for Multimodality
The library implements the VLM2Vec method for training Vision‑Language models that produce effective multimodal embeddings. Presented at ICLR 2025.
// KEY FEATURES
- Training VLM on large image‑text pairs
- Generation of universal multimodal embeddings
- Support for fine‑tuning and zero‑shot search across modalities
#benchmark#contrastive-learning#embedding#image-retrieval#mmeb#multimodal#rag#representation-learning#video-retrieval#visual-document-retrieval#vlm
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram