Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various modalities for a given query. But their practical application is often hindered by the substantial computational cost incurred from processing a large number of tokens from visual inputs. In this paper, we propose Magic-MM-Embedding, a series of novel models that achieve both high efficiency and state-of-the-art performance in universal multimodal embedding. Our approach is built on two synergistic pillars: (1) a highly efficient MLLM architecture incorporating visual token compression to drastically reduce inference latency and memory footprint, and (2) a multi-stage progressive training strategy designed to not only recover but significantly boost performance. This coarse-to-fine training paradigm begins with extensive continue pretraining to restore multimodal understanding and generation capabilities, progresses to large-scale contrastive pretraining and hard negative mining to enhance discriminative power, and culminates in a task-aware fine-tuning stage guided by an MLLM-as-a-Judge for precise data curation. Comprehensive experiments show that our model outperforms existing methods by a large margin while being more inference-efficient.
@article{arxiv.2602.05275,
title = {Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs},
author = {Qi Li and Yanzhe Zhao and Yongxin Zhou and Yameng Wang and Yandong Yang and Yuanjia Zhou and Jue Wang and Zuojian Wang and Jinxiang Liu},
journal= {arXiv preprint arXiv:2602.05275},
year = {2026}
}