Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Your VAR Model is Secretly an Efficient and Explainable Generative Classifier
Yi-Chung Chen, David I. Inouye, Jing Gao
Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts.…
cs.LG2025
GRIT: Out-of-Distribution Robustness from Finite and Noisy Invariant Pairs
Ruqi Bai, Yao Ji, Easton Currie +3
Predictors often exploit spurious correlations that fail under distribution shift, undermining out-of-distribution (OOD) robustness. Invariant pairs, such as the same object photog…