Login / Signup
LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inference.
Zhongwei Wan
Ziang Wu
Che Liu
Jinfa Huang
Zhihong Zhu
Peng Jin
Longyue Wang
Li Yuan
Published in:
CoRR (2024)
Keyphrases
</>
optimization problems
multi modal
optimization process
efficient learning
neural network
bayesian networks
computationally efficient
contextual information
website
query processing
computationally expensive
optimization method
data access
cache conscious