Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models
新概念必须进入之处:统一多模态模型中的入口门跨任务可用性
Zongyang Qiu, Yihan Wu, Kaixuan Fan, Bo Li, Hui Xiong
机构
*
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
;
Columbia University(哥伦比亚大学)
;
CUHK(香港中文大学)
;
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
机构
*
Tsinghua University(清华大学)
;
Massachusetts Institute of Technology(麻省理工学院)
;
Harvard University(哈佛大学)
;
Carnegie Mellon University(卡内基梅隆大学)
;
University of Michigan(密歇根大学)
;
University of Illinois Urbana–Champaign(伊利诺伊大学厄巴纳-香槟分校)
;
Boston University(波士顿大学)
;
University of Queensland(昆士兰大学)
;
University of Science and Technology of China(中国科学技术大学)
;
Flatiron Institute(弗拉蒂伦研究所)
;
Microsoft Research(微软研究院)
;
AG2 AI(AG2 AI公司)
Comments23 pages, 2 figures (11 pages for the main text), for code of implementation and evaluation, see this https URL (https://github.com/youweizhong/PANDA)