5 papers · 1 filter
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…
MemGuard-Alpha: Limits of Membership Inference for Detecting and Filtering Memorization-Contaminated Signals in LLM-Based Financial Forecasting
Anisha Roy, Dip Roy
Large language models are increasingly used to generate financial alpha signals, but many have memorized the historical data in their training corpora, producing apparent accuracy…
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…
A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders
Dip Roy, Rajiv Misra, Sanjay Kumar Singh +1
Understanding how generative models represent and transform data is a foundational problem in deep learning interpretability. While mechanistic interpretability of discriminative a…
Bayesian Autoencoder for Medical Anomaly Detection: Uncertainty-Aware Approach for Brain 2 MRI Analysis
Dip Roy
In medical imaging, anomaly detection is a vital element of healthcare diagnostics, especially for neurological conditions which can be life-threatening. Conventional deterministic…