HiRED: Attention-Guided Token Dropping for Efficient Inference of High-Resolution Vision-Language Models in Resource-Constrained Environments
Paper
•
2408.10945
•
Published
•
11
Hasan Arif
hasanar1f
AI & ML interests
Efficient training and inference
Recent Activity
upvoted
a
paper
about 1 month ago
Round Attention: A Novel Round-Level Attention Mechanism to Accelerate
LLM Inference
upvoted
a
paper
about 2 months ago
From Token to Action: State Machine Reasoning to Mitigate Overthinking
in Information Retrieval
liked
a dataset
4 months ago
anon8231489123/ShareGPT_Vicuna_unfiltered
Organizations
authored
a
paper
11 months ago