internal-activations

Tag

Cards List
#internal-activations

Detecting Neural Network Failures through Spectral Analysis of Internal Activations

arXiv cs.LG · 2026-07-24 Cached

This paper identifies spectral drift in internal activations of neural networks during misclassifications and introduces Self-Detecting Neural Networks (SDNN) that monitors spectral dynamics to detect failures, achieving 79% AUROC on CIFAR-10, outperforming confidence-based methods by 25-30 percentage points.

0 favorites 0 likes
#internal-activations

Reading Calibrated Uncertainty from Language Model Trajectories

arXiv cs.LG · 2026-05-25 Cached

This paper introduces a method to calibrate uncertainty in language models by extracting eleven scale-invariant geometric features from per-layer MLP update trajectories and feeding them to a sparse linear probe, outperforming MSP under selective abstention by up to 21 AURC points.

0 favorites 0 likes
← Back to home

Submit Feedback