VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
Paper
•
2412.02186
•
Published
•
23
•
2
Kangsan Kim
KangsanKim71
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
11 days ago
THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
upvoted
a
paper
about 1 month ago
Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation
upvoted
a
paper
2 months ago
WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
Organizations
None yet
commented
a
paper
about 1 year ago