Skip to content
arXiv cs.LG · Papers

Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference

arXiv:2602.00620v2 Announce Type: replace Abstract: The zero-shot evaluation of time series foundation models (TSFMs) for classification typically uses a frozen encoder followed by a task-specific classifier. However, this practice violates the training-free premise of zero-shot deployment and introduces evaluation bia