1

Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention

We study the problem of monitoring machine learning models under gradual distribution shifts, where circumstances change slowly over time, often leading to unnoticed yet significant declines in accuracy. To address this, we propose Incremental …

Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond

Towards LVLM-Aided Alignment of Task-Specific Vision Models

A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models

Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors

Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance

Provably Better Explanations with Optimized Aggregation of Feature Attributions

Through the Eyes of the Expert: Aligning Human and Machine Attention for Industrial AI

Encoding domain knowledge in multi-view latent variable models: A bayesian approach with structured sparsity

Test Time Augmentation Meets Post-hoc Calibration: Uncertainty Quantification under Real-World Conditions