Home / Publications / Curriculum-Driven 3D CT Report Generation via Language-Free Visual Grafting and Zone-Constrained Compression
Publication

Curriculum-Driven 3D CT Report Generation via Language-Free Visual Grafting and Zone-Constrained Compression

V. K. Cody Bumgardner, Mitchell A. Klusty, Mahmut S. Gokmen, Evan W. Damron

Details

Journal arXiv preprint
Year 2026
Categories cs.CV, cs.AI
Note 10 pages, 2 figures

Abstract

Automated radiology report generation from 3D computed tomography (CT) volumes is challenging due to extreme sequence lengths, severe class imbalance, and the tendency of large language models (LLMs) to ignore visual tokens in favor of linguistic priors. We present Ker-VLJEPA-3B, a four-phase curriculum learning framework for free-text report generation from thoracic CT volumes.

10 pages, 2 figures