AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
Paper
•
2411.12593
•
Published
•
1
Muza
shbhro
AI & ML interests
None yet
Recent Activity
liked
a model
about 1 month ago
nvidia/omnivinci
upvoted
a
paper
about 2 months ago
AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
upvoted
a
paper
about 2 months ago
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding
LLM
Organizations
upvoted
2
papers
about 2 months ago