MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval

As Multimodal Large Language Models (MLLMs) grow in size, adapting them to specialized tasks becomes increasingly challenging due to high computational and memory demands. Indeed, traditional fine-tuning methods are costly, due to the need for extensive, task-specific training. While efficient adaptation methods exist that aim to reduce these costs, in practice they suffer from shallow inter-modal alignment, which severely hurts model effectiveness. To tackle these computational challenges and improve inter-modal alignment, we introduce the MultiWay-Adapter (MWA), a novel framework featuring …

aim computational costs cs.ai cs.cv cs.lg cs.mm fine-tuning image indeed language language models large language large language models memory mllms modal multi-modal multimodal practice reduce retrieval scalable scale tasks task-specific training text them training