2 papers
cs.LG2026
Decafs: Disentangled Conditional adversarial Flows
Anirudh jain, Sakshi Varshney, Samuel Kaski +1
Flow-based models have established state-of-the-art performance in generative modeling across domains, but are hard to interpret due to their complex latent embeddings. In particul…
cs.LG2026
Shortcut Invariance: Targeted Jacobian Regularization in Disentangled Latent Space
Shivam Pal, Sakshi Varshney, Piyush Rai
Deep neural networks are prone to learning shortcuts, spurious correlations present in the training data that undermine out-of-distribution (OOD) generalization. Most prior work mi…