이미지 설명하는 LLM 최신 - MoAI

https://paperswithcode.com/paper/moai-mixture-of-all-intelligence-for-large

Papers with Code - MoAI: Mixture of All Intelligence for Large Language and Vision Models #17 best model for Visual Question Answering on MM-Vet (GPT-4 score metric) #17 best model for Visual Question Answering on MM-Vet (GPT-4 score metric)

https://github.com/ByungKwanLee/MoAI

GitHub - ByungKwanLee/MoAI: Official PyTorch implementation code for realizing the technical part of Mixture of All Intelligence (MoAI) to improve performance of numerous zero-shot vision language tasks. (Under Review) Official PyTorch implementation code for realizing the technical part of Mixture of All Intelligence (MoAI) to improve performance of numerous zero-shot vision language tasks. (Under Review) - Byun… Official PyTorch implementation code for realizing the technical part of Mixture of All Intelligence (MoAI) to improve performance of numerous zero-shot vision language tasks. (Under Review) - Byun…

LLAVA 1.5 까지는 검색으로 알고 있었는데 최근 더 성능 높다고 하는 모델이 나왔네요 ㅎㅎ 대단