Xinchen Zhang's picture

Xinchen Zhang

comin

·

https://cominclip.github.io/

Cominclip

AI & ML interests

None yet

Recent Activity

upvoted a paper 9 days ago

Reconstruction Alignment Improves Unified Multimodal Models

liked a model about 1 month ago

sanaka87/BAGEL-RecA

upvoted a paper 2 months ago

AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning

View all activity

Organizations

None yet

Papers 6

arxiv:2505.15809

arxiv:2505.07062

arxiv:2502.12148

arxiv:2502.12146

spaces 1

IterComp

IterComp: Iterative Composition-Aware Feedback Learning from

models 1

comin/IterComp

Text-to-Image • Updated Feb 19 • 1.16k • 53

datasets 3

comin/face-data3

Updated May 12 • 5

comin/face-syner

Updated May 10 • 3

comin/id_test

Updated Apr 21 • 10