notesum.ai

Published at May 7

Efficient Large Multi-modal Models via Visual Context Compression

NeurIPS

Released Date: May 7, 2024

Authors: Jieneng Chen1, Luoxin Ye1, Ju He1, Zhao-Yang Wang1, Daniel Khashabi1, Alan Yuille1

Aff.: 1Johns Hopkins University

Arxiv: https://openreview.net/pdf/8464f557e0eafcebf6b3307cb864bf60aee57ec6.pdf