Pratik Mazumder

Logit-Origin Centering for Singleton Test-Time Adaptation

This paper argues that singleton tabular FTTA is not merely a small-batch variant of ordinary FTTA, but a distinct identifiability problem where only the location of the model's score stream remains directly observable, and proposes Prequential Logit-Origin Centering (PLOC), a lightweight approach that keeps the source model frozen and shifts the logit space at each step.