Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation
Paper
•
2505.18842
•
Published
•
36
Junhyeok Kim
kjunh
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning
Segmentation
new activity
about 1 month ago
kjunh/v1g-sample:Enhance dataset card: Add paper, code, project page, abstract, citation, task categories, and tags
updated
a model
4 months ago
mirlabcollaboration/v1-internvl2.5-fix-image-size-448-7B-checkpoint-22000
Organizations
authored
a
paper
6 months ago
authored
a
paper
9 months ago