Junjie Fei's picture

Junjie Fei

FeiElysia

AI & ML interests

None yet

Recent Activity

authored a paper 1 day ago

Caption Anything: Interactive Image Description with Diverse Multimodal Controls

authored a paper 1 day ago

Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents

authored a paper 1 day ago

WikiAutoGen: Towards Multi-Modal Wikipedia-Style Article Generation

View all activity

Organizations

None yet

Papers 6

arxiv:2604.08120

arxiv:2604.06425

arxiv:2503.19065

arxiv:2411.16740

models 0

None public yet

datasets 0

None public yet