Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning.

Bingchen Zhao Haoqin Tu Chen Wei Jieru Mei Cihang Xie

Published in: CoRR (2023)

Keyphrases

multi modal
multi modality
audio visual
high dimensional
semantic concepts
cross modal
image annotation
data sources
image registration
image classification
video data
video search