SOURCE-LINKED INTELLIGENCE

SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are converted into tabular representations. Existing representations face two challenges: global aggregation can lose the order of temporal evolution, while features computed in independently fitted coordinate systems may not have consistent meanings across sequences. We therefore view representation design for TFMs as a problem in its own right: the representation should preserve local temporal transitions while maintaining a shared feature definitio

Read original source ↗ Open in workspace

recordType

paper

region

Global