N. S. Shaik, T. K. Cherukuri, A. Masood, and D. Hye Ye, “DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities”, AAAI, vol. 40, no. 11, pp. 8814–8823, Mar. 2026.