VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning
Paper
•
2504.07960
•
Published
•
50
Juncheng Yan
JonsonYan
·
AI & ML interests
3D computer vision
Recent Activity
upvoted
a
paper
about 5 hours ago
Ministral 3
liked
a model
4 months ago
Alpha-VLLM/Lumina-DiMOO
upvoted
a
paper
6 months ago
Scaling RL to Long Videos
Organizations
None yet
authored
a
paper
9 months ago