Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data

ArXi:2603.27135v1 Announce Type: new Text-to-time-series generation is particularly important in meteorology, where natural language offers intuitive control over complex, multi-scale atmospheric dynamics. Existing approaches are constrained by the lack of large-scale, physically grounded multimodal datasets and by architectures that overlook the spectral-temporal structure of weather signals. We address these challenges with a unified framework for text-guided meteorological time-series generation. First, we.