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 and fine-tuning 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 4.5X, fine-tuning memory usage by 3.4X, pre-filling latency by 1.6-2.2X, and decoding latency by 1.2-2.8X. We will soon make our code and models available to facilitate reproducibility.

翻译：近年来，视觉语言模型在准确性方面取得了显著进展，但其效率却鲜受关注。本文介绍了NVILA系列——一个旨在同时优化效率与准确性的开源视觉语言模型家族。基于VILA架构，我们首先通过提升空间与时间分辨率进行模型扩展，随后对视觉标记进行压缩。这种“先扩展后压缩”的方法使NVILA能够高效处理高分辨率图像与长视频。我们进一步开展了系统性研究，以提升NVILA在全生命周期（涵盖训练、微调至部署各阶段）的效率。在广泛的图像与视频基准测试中，NVILA达到或超越了众多领先的开源及专有视觉语言模型的准确性。同时，其训练成本降低了4.5倍，微调内存占用减少了3.4倍，预填充延迟降低了1.6-2.2倍，解码延迟降低了1.2-2.8倍。我们将很快公开代码与模型以促进可复现性研究。