Rais, K., Mohamed Amroune, Haouam, M.Y. and Benmachiche, A. 2025. CAT-VAE: A Cross-Attention Transformer-Enhanced Variational Autoencoder for Improved Image Synthesis. Statistics, Optimization & Information Computing. 14, 5 (Jul. 2025), 2534-2558. DOI:https://doi.org/10.19139/soic-2310-5070-2546.