3 papers
cs.LG2026
From Uncertainty to Failure Attribution: Self-Diagnosing Models for Failure Attribution under Distribution Shift
Yiyao Yang
Distribution shift poses a significant challenge to the robustness of machine learning models, but the current solutions only aim to detect out-of-distribution (OOD) samples and pr…
stat.ML2026
Beyond Predictive Uncertainty: Reliable Representation Learning with Structural Constraints
Yiyao Yang
Uncertainty estimation in machine learning has traditionally focused on the prediction stage, aiming to quantify confidence in model outputs while treating learned representations…
q-bio.GN2026
Robust Machine Learning for Regulatory Sequence Modeling under Biological and Technical Distribution Shifts
Yiyao Yang
Robust machine learning for regulatory genomics is studied under biologically and technically induced distribution shifts. Deep convolutional and attention based models achieve str…