230313 Scaling Vision-Language Models with Sparse Mixture of Experts.md

https://arxiv.org/abs/2303.07226

Scaling Vision-Language Models with Sparse Mixture of Experts (Sheng Shen, Zhewei Yao, Chunyuan Li, Trevor Darrell, Kurt Keutzer, Yuxiong He)

moe vision-language 모델이군요. moe 모델은 늘 유망주라는 느낌인데 급부상할 시점이 올까요. 좀 궁금하긴 합니다.

#mixture_of_experts #vision-language