AI RESEARCH
STEP: Scientific Time-Series Encoder Pretraining via Cross-Domain Distillation
arXiv CS.LG
•
ArXi:2603.18688v1 Announce Type: new Scientific time series are central to scientific AI but are typically sparse, highly heterogeneous, and limited in scale, making unified representation learning particularly challenging. Meanwhile, foundation models pretrained on relevant time series domains such as audio, general time series, and brain signals contain rich knowledge, but their applicability to scientific signals remains underexplored.