HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments
Paper
•
2408.10945
•
Published
•
6
•
2
Hasan Arif
hasanar1f
AI & ML interests
Efficient training and inference
Organizations
hasanar1f's activity
commented
a
paper
3 months ago