OneCast: Structured Decomposition and Modular Generation for Cross-Domain Time Series Forecasting
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学);Institute for Clarity in Documentation(文档清晰性研究所);Inria Paris-Rocquencourt(巴黎-鲁克隆研究所);Rajiv Gandhi University(拉贾·甘地大学);Tsinghua University(清华大学);Palmer Research Laboratories(帕勒尔研究实验室)
Cross-domain time series forecasting is a valuable task in various web applications. Despite its rapid advancement, achieving effective generalization across heterogeneous time series data remains a significant challenge. Existing methods have made progress by extending single-domain models, yet often fall short when facing domain-specific trend shifts and inconsistent periodic patterns. We argue that a key limitation lies in treating temporal series as undifferentiated sequence, without explicitly decoupling their inherent structural components. To address this, we propose OneCast, a structured and modular forecasting framework that decomposes time series into seasonal and trend components, each modeled through tailored generative pathways. Specifically, the seasonal component is captured by a lightweight projection module that reconstructs periodic patterns via interpretable basis functions. In parallel, the trend component is encoded into discrete tokens at segment level via a semantic-aware tokenizer, and subsequently inferred through a masked discrete diffusion mechanism. The outputs from both branches are combined to produce a final forecast that captures seasonal patterns while tracking domain-specific trends. Extensive experiments across eight domains demonstrate that OneCast mostly outperforms state-of-the-art baselines.
Evaluating the Sensitivity of BiLSTM Forecasting Models to Sequence Length and Input Noise
King Fahd University of Petroleum \& Minerals, Department of Information;Computer Science, Dhahran, Saudi Arabia Imam Abdulrahman Bin Faisal University, Department of Computer Science SDAIA-KFUPM Joint Research Center for Artificial Intelligence, Dhahran, Saudi Arabia
pyFAST: A Modular PyTorch Framework for Time Series Modeling with Multi-source and Sparse Data
College of Computer Engineering, Jimei University(嘉应大学计算机工程学院);Chengyi College, Jimei University(嘉应大学 Chengyi 学院);Department of Technology, Management and Economics, Technical University of Denmark(丹麦技术大学技术、管理与经济系)
MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition
Department of Computer Science, National University of Singapore(新加坡国立大学计算机科学系);University College London(伦敦大学学院);University of Edinburgh(爱丁堡大学);Data & Analytics, Digital X(Digital X 数据与分析部);Alan Turing Institute(艾伦·图灵研究所)