LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models.

Yuzhang Shang Mu Cai Bingxin Xu Yong Jae Lee Yan Yan

Published in: CoRR (2024)

Keyphrases

multi modal
computer vision
probabilistic model
statistical model
cost effective
statistical models
learning algorithm
artificial intelligence
knowledge base
three dimensional
similarity measure
lightweight
statistical methods
mathematical models
hybrid model
audio visual