Multimodal Foundation Models: From Specialists to General-Purpose Assistants
MultimodalFoundationModels:FromSpecialiststoGeneral-PurposeAssistants基本信息博客贡献人燕青作者ChunyuanLi,ZheGan,ZhengyuanYang,etal.标签LLM,Multimodality摘要近年来,人工智能领域在模型发展方面经历4个阶段,如图1所示。任务特定的模型是针对单个数据集和任务开发的,通常从零开始训练