Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images.

Kuofeng Gao Yang Bai Jindong Gu Shu-Tao Xia Philip Torr Zhifeng Li Wei Liu

Published in: ICLR (2024)

Keyphrases

language model
high energy
image data
language modeling
image features
document retrieval
image retrieval
probabilistic model
n gram
image database
information retrieval
image collections
retrieval model
speech recognition
statistical language models
test collection
image understanding
smoothing methods
context sensitive
language modelling
ad hoc information retrieval
document ranking
vector space model
image annotation
image regions
document collections
image classification
computer vision