Wensong Song's picture

2 6 6

Wensong Song

WensongSong

·

AI & ML interests

None yet

Recent Activity

liked a Space 8 days ago

akhaliq/sora-2

upvoted a paper about 2 months ago

Visual Representation Alignment for Multimodal Large Language Models

upvoted a paper about 2 months ago

Reconstruction Alignment Improves Unified Multimodal Models

View all activity

Organizations

spaces 2

Insert Anything

Insert images into backgrounds using masks or text labels

Segment

Segment objects in images using text prompts

models 1

WensongSong/Insert-Anything

Updated Apr 24 • 14

datasets 2

WensongSong/AnyInsertion_V1

Viewer • Updated May 9 • 137k • 2.06k • 3

WensongSong/AnyInsertion

Viewer • Updated May 9 • 59k • 706 • 9