Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
Paper
•
2510.19592
•
Published
•
12
Su Ho Han
ciplabhan
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
24 days ago
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning
Segmentation
updated
a dataset
about 1 month ago
CIPLab-Video/DecAF_output
upvoted
a
paper
6 months ago
Multi-Granular Spatio-Temporal Token Merging for Training-Free
Acceleration of Video LLMs
Organizations
