SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Paper
•
2503.08625
•
Published
•
22
Hao Chen
yanjiamao
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 19 hours ago
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by
Imitating Human Annotator Trajectories
upvoted
a
paper
14 days ago
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
Organizations
None yet