alessiasaporita/

MissRAG

This repository provides precomputed multimodal embeddings and modality tokens used in the MissRAG framework:

MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models

We release:

🔹 ImageBind-based embeddings for multimodal retrieval 🔹 Precomputed modality tokens (audio/video) for efficient inference

These representations are designed to:

enable retrieval across modalities support… See the full description on the dataset page: https://huggingface.co/datasets/alessiasaporita/MissRAG.