MoE-TinyMed: Mixture of Experts for Tiny Medical Large Vision-Language Models

arXiv:2404.10237v1 Announce Type: cross
Abstract: Mixture of Expert Tuning (MoE-Tuning) has effectively enhanced the performance of general MLLMs with fewer parameters, yet its application in resource-limited medical settings has not been fully explored. To address this gap, we developed MoE-TinyMed, a model tailored for medical applications that significantly lowers parameter demands. In evaluations on the VQA-RAD, SLAKE, and Path-VQA datasets, MoE-TinyMed outperformed LLaVA-Med in all Med-VQA closed settings with just 3.6B parameters. Additionally, a streamlined version with 2B parameters surpassed …

abstract application applications arxiv cs.cl cs.cv expert experts gap general language language models medical mixture of experts mllms moe parameters performance type vision vision-language vision-language models