Search papers, labs, and topics across Lattice.
This paper introduces ChorusTIC, a novel classification-native foundation model designed for multivariate time series classification that operates without the need for task-specific parameter updates. By employing episode-consistent Random Subchannel Slot Concatenation alongside a shared dual-axis encoder, ChorusTIC effectively captures temporal and cross-channel interactions, allowing it to generate a fixed-width representation regardless of the number of input channels. Evaluations on the UEA-30 and UCR-128 datasets demonstrate that ChorusTIC achieves robust performance in both full-context and low-label scenarios, outperforming traditional methods that require individual classifier fitting.
ChorusTIC achieves strong multivariate time series classification without the need for retraining on specific tasks, revolutionizing how we approach classification in heterogeneous data environments.
Time series classification underpins applications in healthcare, sensing, and industrial monitoring. Although time series foundation models support forecasting and transferable representation learning, classification still typically requires fitting a task-specific classifier on each target dataset, while individual channels of multivariate inputs are often encoded independently. We introduce ChorusTIC, a classification-native foundation model for in-context classification across heterogeneous channel configurations without target-task parameter updates. ChorusTIC combines episode-consistent Random Subchannel Slot Concatenation with a shared dual-axis encoder to model temporal and cross-channel interactions and map variable channel configurations into a fixed-width representation independent of the original channel count. It then calibrates feature axes using context-derived distributions and predicts query labels through leakage-protected in-context learning. We pretrain ChorusTIC solely on synthetic labeled episodes comprising context and query sets that share a task background, with classes distinguished by sparse temporal or cross-channel rules. Evaluations on the complete UEA-30 and UCR-128 archives show strong full-context and low-label performance without target-specific classifier fitting.
