3 papers
cs.LG2026
ORBIT: Autoregressive Time Series Generation via Next Frequency-Band Prediction
Chunyi Hou, Xiangfei Qiu, Hanyin Cheng +5
Deep generative models provide an effective modern solution to alleviating the problem of data scarcity by synthesizing realistic time series. However, despite the considerable pro…
cs.LG2026
Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain Generalization
Tengxue Zhang, Yu Ke, Yang Shu +4
Temporal Domain Generalization (TDG) has emerged to address real-world streaming data with distribution shifts over time. However, existing methods are either prone to overfitting…
cs.LG2026
SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning
Yi Tang, Tengxue Zhang, Yang Shu +3
Time Series Foundation Models (TSFMs) have achieved remarkable zero-shot performance through extensive pre-training on massive time series datasets. Nevertheless, due to the low-di…