Token-Efficient Long Video Understanding for Multimodal LLMs
Paper
•
2503.04130
•
Published
•
70
Yaru Niu
chrisyrniu
AI & ML interests
Robotics, Machine Learning, Reinforcement Learning, Multi-Agent Systems
Recent Activity
upvoted
a
paper
3 days ago
Token-Efficient Long Video Understanding for Multimodal LLMs
upvoted
a
paper
6 months ago
Agile Continuous Jumping in Discontinuous Terrains
authored
a paper
over 1 year ago
Creative Robot Tool Use with Large Language Models
Organizations
None yet