Generative Diffusion Prior Distillation for Long-Context Knowledge Transfer

arXiv:2605.11414v1 Announce Type: cross Abstract: While traditional time-series classifiers assume full sequences at inference, practical constraints (latency and cost) often limit inputs to partial prefixes. The absence of class-discriminative patterns in partial data can significantly hinder a classifier's ability to generalize. This work uses knowledge distillation (KD) to equip partial time series classifiers with the generalization ability of their full-sequence counterparts. In KD, high-ca