ML Anthology

NVILA: Efficient Frontier Visual Language Models

Zhijian Liu, Ligeng Zhu, Baifeng Shi, Zhuoyang Zhang, Yuming Lou, Shang Yang, Haocheng Xi, Shiyi Cao, Yuxian Gu, Dacheng Li, Xiuyu Li, Haotian Tang, Yunhao Fang, Yukang Chen, Cheng-Yu Hsieh, De-An Huang, An-Chieh Cheng, Jinyi Hu, Sifei Liu, Ranjay Krishna, Pavlo Molchanov, Jan Kautz, Hongxu Yin, Song Han, Yao Lu
CVPR 2025 pp. 4122-4134
doi:10.1109/CVPR52734.2025.00390 /cvpr/2025/liu2025cvpr-nvila/

Abstract

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 optimize both 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 also conduct a systematic investigation to enhance the efficiency of NVILA throughout its entire lifecycle, from training to deployment. NVILA matches or surpasses the accuracy of many leading open and proprietary VLMs across a wide range of image and video benchmarks. At the same time, it reduces training costs by 1.9-5.1X, prefilling latency by 1.6-2.2X, and decoding latency by 1.2-2.8X.

PDF CVPR Semantic Scholar

Cite

Text

Liu et al. "NVILA: Efficient Frontier Visual Language Models." Conference on Computer Vision and Pattern Recognition, 2025. doi:10.1109/CVPR52734.2025.00390

Markdown

[Liu et al. "NVILA: Efficient Frontier Visual Language Models." Conference on Computer Vision and Pattern Recognition, 2025.](https://mlanthology.org/cvpr/2025/liu2025cvpr-nvila/) doi:10.1109/CVPR52734.2025.00390

BibTeX

@inproceedings{liu2025cvpr-nvila,
  title     = {{NVILA: Efficient Frontier Visual Language Models}},
  author    = {Liu, Zhijian and Zhu, Ligeng and Shi, Baifeng and Zhang, Zhuoyang and Lou, Yuming and Yang, Shang and Xi, Haocheng and Cao, Shiyi and Gu, Yuxian and Li, Dacheng and Li, Xiuyu and Tang, Haotian and Fang, Yunhao and Chen, Yukang and Hsieh, Cheng-Yu and Huang, De-An and Cheng, An-Chieh and Hu, Jinyi and Liu, Sifei and Krishna, Ranjay and Molchanov, Pavlo and Kautz, Jan and Yin, Hongxu and Han, Song and Lu, Yao},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2025},
  pages     = {4122-4134},
  doi       = {10.1109/CVPR52734.2025.00390},
  url       = {https://mlanthology.org/cvpr/2025/liu2025cvpr-nvila/}
}