VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
Paper
•
2504.07960
•
Published
•
50
Zhong-Yu Li
lzyhha
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
15 days ago
Gaussian Splatting with Discretized SDF for Relightable Assets
upvoted
a
paper
about 1 month ago
FLUX.1 Kontext: Flow Matching for In-Context Image Generation and
Editing in Latent Space
upvoted
a
paper
about 1 month ago
LLaVA-Scissor: Token Compression with Semantic Connected Components for
Video LLMs
Organizations
authored
a
paper
4 months ago