Surveying the MLLM Landscape: A Meta-Review of Current Surveys
测绘MLLM景观:当前调研的元综述
机构 * Georgia Institute of Technology(佐治亚理工学院) ; Indiana University(印第安纳大学) ; Purdue University(普渡大学) ; Emory University(埃默里大学) ; Sichuan University(四川大学) ; Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学) ; AppCubic ; Kyoto University(京都大学) ; University of Wisconsin-Madison(威斯康星大学麦迪逊分校) ; Rutgers University(罗格斯大学) ; National Taiwan Normal University(台湾师范大学)
AI总结 本文通过系统回顾现有调研,全面分析MLLMs的评估方法、挑战与趋势,为研究者提供当前评估现状的深入理解。
Comments The article consists of 22 pages, including 2 figures and 108 references. The paper provides a meta-review of surveys on Multimodal Large Language Models (MLLMs), categorizing findings into key areas such as evaluation, applications, security, and future directions