Table of Contents: :: Library Catalog

Saved in:

Bibliographic Details
Main Authors:	Liu, Zhijian, Zhu, Ligeng, Shi, Baifeng, Zhang, Zhuoyang, Lou, Yuming, Yang, Shang, Xi, Haocheng, Cao, Shiyi, Gu, Yuxian, Li, Dacheng, Li, Xiuyu, Fang, Yunhao, Chen, Yukang, Hsieh, Cheng-Yu, Huang, De-An, Cheng, An-Chieh, Nath, Vishwesh, Hu, Jinyi, Liu, Sifei, Krishna, Ranjay, Xu, Daguang, Wang, Xiaolong, Molchanov, Pavlo, Kautz, Jan, Yin, Hongxu, Han, Song, Lu, Yao
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	https://arxiv.org/abs/2412.04468
Tags:	Add Tag No Tags, Be the first to tag this record!

Table of Contents:

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency and accuracy. Building on top of VILA, we improve its model architecture by first scaling up the spatial and temporal resolutions, and then compressing visual tokens. This "scale-then-compress" approach enables NVILA to efficiently process high-resolution images and long videos. We further conduct a systematic investigation that enhances NVILA's efficiency throughout its entire lifecycle, from training and fine-tuning to deployment. NVILA matches or surpasses the accuracy of leading open and proprietary VLMs across a wide range of image and video benchmarks. At the same time, it reduces training cost by 1.9-5.1x, prefilling latency by 1.6-2.2x, and decoding latency by 1.2-2.8x. We release our code and models to facilitate reproducibility.

Similar Items