SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Paper
•
2503.08625
•
Published
•
26
ViaKai
ViaKai
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by
Imitating Human Annotator Trajectories
liked
a dataset
about 2 months ago
TIGER-Lab/OmniEdit-Filtered-1.2M
upvoted
a
paper
about 2 months ago
DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks
Organizations
None yet