7 papers
NVILA: Efficient Frontier Visual Language Models
Zhijian Liu, Ligeng Zhu, Baifeng Shi +24
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…
LUMEN: Longitudinal Multi-Modal Radiology Model for Prognosis and Diagnosis
Zhifan Jiang, Dong Yang, Vishwesh Nath +7
Large vision-language models (VLMs) have evolved from general-purpose applications to specialized use cases such as in the clinical domain, demonstrating potential for decision sup…
MAISI: Medical AI for Synthetic Imaging
Pengfei Guo, Can Zhao, Dong Yang +8
Medical imaging analysis faces challenges such as data scarcity, high annotation costs, and privacy concerns. This paper introduces the Medical AI for Synthetic Imaging (MAISI), an…
No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models
Min Woo Sun, Alejandro Lozano, Javier Gamazo Tejero +8
Embedding vision-language models (VLMs) are typically pretrained with short text windows (<77 tokens), which forces the truncation of long-format captions. Yet, the distribution of…
Unified Supervision For Vision-Language Modeling in 3D Computed Tomography
Hao-Chih Lee, Zelong Liu, Hamza Ahmed +6
General-purpose vision-language models (VLMs) have emerged as promising tools in radiology, offering zero-shot capabilities that mitigate the need for large labeled datasets. Howev…
Text2CT: Towards 3D CT Volume Generation from Free-text Descriptions Using Diffusion Model
Pengfei Guo, Can Zhao, Dong Yang +9
Generating 3D CT volumes from descriptive free-text inputs presents a transformative opportunity in diagnostics and research. In this paper, we introduce Text2CT, a novel approach…