Author name: Dip Roy, Rajiv Misra, Sanjay Kumar Singh, Anisha Roy

arXiv:2505.03530v3 Announce Type: replace
Abstract: Understanding how generative models represent and transform data is a foundational problem in deep learning interpretability. While mechanistic interpretability of discriminative architectures has yi…

arXiv:2603.21236v2 Announce Type: replace
Abstract: Although mechanism-based interpretability has generated an abundance of insight for discriminative network analysis, generative models are less understood — particularly outside of image-related app…