E5-V: Universal Embeddings with Multimodal Large Language Models
This addresses the challenge of costly multimodal data collection and training for researchers and practitioners in multimodal AI, though it appears incremental as it builds on existing MLLM capabilities.
The paper tackles the problem of representing multimodal information using multimodal large language models (MLLMs) by introducing E5-V, a framework that adapts MLLMs for universal multimodal embeddings. The result shows that E5-V achieves or surpasses state-of-the-art performance across four task types while reducing training costs by approximately 95% through single-modality text-only training.
Multimodal large language models (MLLMs) have shown promising advancements in general visual and language understanding. However, the representation of multimodal information using MLLMs remains largely unexplored. In this work, we introduce a new framework, E5-V, designed to adapt MLLMs for achieving universal multimodal embeddings. Our findings highlight the significant potential of MLLMs in representing multimodal inputs compared to previous approaches. By leveraging MLLMs with prompts, E5-V effectively bridges the modality gap between different types of inputs, demonstrating strong performance in multimodal embeddings even without fine-tuning. We propose a single modality training approach for E5-V, where the model is trained exclusively on text pairs. This method demonstrates significant improvements over traditional multimodal training on image-text pairs, while reducing training costs by approximately 95%. Additionally, this approach eliminates the need for costly multimodal training data collection. Extensive experiments across four types of tasks demonstrate the effectiveness of E5-V. As a universal multimodal model, E5-V not only achieves but often surpasses state-of-the-art performance in each task, despite being trained on a single modality.