SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by Imitating Human Annotator Trajectories
Paper
•
2503.08625
•
Published
•
26
•
2
zhumuzhi
Z-MU-Z
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 3 hours ago
VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal
Large Language Models
upvoted
a
paper
about 1 month ago
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive
Reinforcement
upvoted
a
paper
about 1 month ago
SegAgent: Exploring Pixel Understanding Capabilities in MLLMs by
Imitating Human Annotator Trajectories
Organizations
None yet
Z-MU-Z's activity
commented
a
paper
about 1 month ago