Time Series Forecasting

Cryptocurrency markets exhibit extreme volatility and non-stationary dynamics that challenge conventional forecasting methods. Although Large Language Models (LLMs) have shown promise for time series forecasting, the com…

parameter-efficient fine-tuning Time Series Forecasting

MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting

2026-09-04 · Yifang Zhang, Shengwu Xiong, Henan Wang, Wenjie Yin 외 arxiv

Accurate station-level precipitation nowcasting is critical for agriculture, water resource management, and disaster prevention, which typically is formulated as a time series forecasting problem. However, conventional t…

Time Series Forecasting

Learning to Difference: Adaptive Reversible Differencing (AdaRDiff) for Time Series Forecasting

2026-08-28 · Morad Laglil, Younes Hlal, Marouane El Hadari, Emilie Devijver 외 arxiv

Reliable long-horizon time series forecasting is an important yet difficult problem. Trends and seasonality introduce complex temporal structure that challenges learning-based forecasting models. Differencing, which subt…

Time Series Forecasting

SAGE: Variate-Wise Semantic Augmentation for Vision-Language Time Series Forecasting

2026-08-27 · Haizhao Fan, Xinyi Le arxiv

Time series forecasting models operate on raw numerical sequences, lacking the semantic knowledge that domain experts implicitly leverage, such as the physical meaning of each variable, its statistical behavior, and its …

Time Series Forecasting

CEDAR: Controlled and Event-Driven Demand Forecasting via Residual Decomposition

2026-08-26 · Junjie Meng, Ranxu Zhang, Zi-an Zhang, Shujun Liu 외 arxiv

Forecasting in large-scale e-commerce marketplaces is increasingly required to support planning: merchants need to evaluate sales outcomes under future action sequences such as budget schedules, rather than passively pre…

Time Series Forecasting

Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time series

2026-08-26 · Annunziata D'Aversa, Gianvito Pio, Michelangelo Ceci arxiv

Forecasting future measurements from geographically distributed sensors is essential across many domains. However, the spatial distribution of these sensors raises multiple challenges, primarily due to spatial autocorrel…

Time Series Forecasting

전체 2,080편 보기 →