Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection 事件

Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection arXiv:2603.12916v3 Announce Type: replace-cross Abstract: Multivariate time series anomalies often manifest as shifts in cross-channel dependencies rather than simple amplitude excursions. In autonomous driving, for instance, a steering command might be internally consistent but decouple from the resulting lateral acceleration. Residual-based detectors can miss such anomalies when flexible sequence models still