Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
Paper
•
2510.19592
•
Published
•
12
Hanjung Kim
HanjungKim
AI & ML interests
Video Understanding, Robot Learning
Recent Activity
upvoted
a
paper
7 days ago
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning
Segmentation
upvoted
a
paper
2 months ago
Less is More: Recursive Reasoning with Tiny Networks
upvoted
a
paper
3 months ago
Autoregressive Universal Video Segmentation Model
Organizations
None yet