Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data
Dip Roy, Rajiv Misra, Sanjay Kumar Singh +1
Although mechanism-based interpretability has generated an abundance of insight for discriminative network analysis, generative models are less understood -- particularly outside o…
cs.LG2026
Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse
Dip Roy, Rajiv Misra, Sanjay Kumar Singh
Extreme neural network sparsification (90% activation reduction) presents a critical challenge for mechanistic interpretability: understanding whether interpretable features surviv…