Mitigating Feature Overfitting in Barlow Twins via Mixed-Sample Regularization for Stable Long-Horizon Representation Learning. Computational Discovery and Intelligent Systems (CDIS), [S. l.], v. 3, n. 1, p. 71–90, 2026. DOI: 10.66279/7scztv14. Disponível em: https://pub.scientificirg.com/index.php/CDIS/article/view/231. Acesso em: 7 may. 2026.