Given the significant potential of large language models (LLMs) in sequence modeling, emerging studies have begun applying them to time-series forecasting. Despite notable progress, existing methods still face two critical challenges: 1) their reliance on large amounts of paired text data, limiting the model applicability, and 2) a substantial modality gap between text and time series, leading to insufficient alignment and suboptimal performance. In this paper, we introduce \textbf{H}ierarchical \textbf{T}ext-\textbf{F}ree \textbf{A}lignment (\textbf{TS-HTFA}), a novel method that leverages hierarchical alignment to fully exploit the representation capacity of LLMs while eliminating the dependence on text data. Specifically, we replace paired text data with adaptive virtual text based on QR decomposition word embeddings and learnable prompt. Furthermore, we establish comprehensive cross-modal alignment at three levels: input, feature, and output. Extensive experiments on multiple time-series benchmarks demonstrate that HTFA achieves state-of-the-art performance, significantly improving prediction accuracy and generalization.
Advancing Real-time Pandemic Forecasting Using Large Language Models: A COVID-19 Case Study
Johns Hopkins University(约翰斯·霍普金斯大学);Mila - Quebec AI Institute(米拉-魁北克人工智能研究所);Harvard T.H. Chan School of Public Health(哈佛陈曾熙公共卫生学院);Harvard University(哈佛大学);Universite de Montréal(蒙特利尔大学);Duke University(杜克大学);Johns Hopkins Bloomberg School of Public Health(约翰斯·霍普金斯大学布隆伯格公共卫生学院)
Advancing Long-Term Multi-Energy Load Forecasting with Patchformer: A Patch and Transformer-Based Approach
School of Mathematics, Statistics and Actuarial Science(数学、统计与精算科学学院);University of Essex(埃塞克斯大学);Alliance Manchester Business School(曼彻斯特联盟商学院);University of Manchester(曼彻斯特大学)
Inertial Confinement Fusion Forecasting via Large Language Models
Rochester Institute of Technology(罗切斯特理工学院);University of Rochester(罗切斯特大学);Meta AI;University of California, Los Angeles(加利福尼亚大学洛杉矶分校);Pacific Northwest National Laboratory(太平洋西北国家实验室)
Advancing Enterprise Spatio-Temporal Forecasting Applications: Data Mining Meets Instruction Tuning of Language Models For Multi-modal Time Series Analysis in Low-Resource Settings
msData: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models
Department of Computer Science, Aalborg University, Aalborg, Denmark(奥尔堡大学计算机科学系);IBM Research Europe, Dublin, Ireland(IBM欧洲研究院);Trinity College Dublin, The University of Dublin, Dublin, Ireland(都柏林大学三一学院)
SuryaBench: Benchmark Dataset for Advancing Machine Learning in Heliophysics and Space Weather Prediction
Earth System Science Center, University of Alabama in Huntsville, AL, USA(阿拉巴马大学亨茨维尔分校地球系统科学中心);NASA Marshall Space Flight Center, Huntsville, AL, USA(美国国家航空航天局马歇尔航天飞行中心);Department of Space Science, The University of Alabama in Huntsville, AL, USA(阿拉巴马大学亨茨维尔分校空间科学系);Center for Space Plasma and Aeronomic Research (CSPAR), The University of Alabama in Huntsville, AL, USA(阿拉巴马大学亨茨维尔分校空间等离子体与航空研究中心);IBM Research(IBM研究院);Georgia State University(佐治亚州立大学);Southwest Research Institute(西南研究院);Princeton University(普林斯顿大学);SETI Institute(搜寻地外文明研究所);Laboratory for Atmospheric and Space Physics, University of Colorado Boulder(科罗拉多大学博尔德分校大气与空间物理实验室);NASA Goddard Space Flight Center(美国国家航空航天局戈达德空间飞行中心)
Towards Explainable Traffic Flow Prediction with Large Language Models
Hong Kong University of Science and Technology (Guangzhou)(香港理工大学(广州));Johns Hopkins University(约翰霍普金斯大学);Department of Civil and System Engineering(土木与系统工程系)
Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics
University at Albany, State University of New York(纽约州立大学奥尔巴尼分校);Digital Financial Information Technology Co.LTD(数字金融信息技术有限公司);Northern Arizona University(北亚利桑那大学)
RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges
The Hong Kong University of Science and Technology(香港科学与技术大学);Nanjing University(南京大学);Southern University of Science and Technology(南方科技大学);Shanghai AI Laboratory(上海人工智能实验室);Shanghai TechWind Technology Co., Ltd.(上海技风科技有限公司)
Advancing Ocean State Estimation with efficient and scalable AI
Department of Earth System Science, Ministry of Education Key Laboratory for Earth System Modeling, Institute for Global Change Studies, Tsinghua University(地球系统科学系、教育部地球系统模拟关键实验室、全球变化研究院、清华大学)
Learning Time-aware Graph Structures for Spatially Correlated Time Series Forecasting
Southwest Jiaotong University(西南交通大学);East China Normal University(华东师范大学);Aalborg University(奥尔堡大学);University of Electronic Science and Technology of China(电子科技大学);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Data-driven ensemble prediction of the global ocean
Artificial Intelligence Innovation and Incubation Institute(人工智能创新与孵化院);Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院);Department of Atmospheric and Oceanic Sciences(大气科学与海洋科学系);Shanghai Academy of Artificial Intelligence for Science(上海人工智能科学研究院);FuXi Intelligent Computing Technology Co., Ltd.(复西智能计算技术有限公司)
Data re-uploading in Quantum Machine Learning for time series: application to traffic forecasting
School of Production Engineering and Management, Technical University of Crete(克里特技术大学生产工程与管理学院);Quantum Innovation Pc(量子创新公司);Alma-Sistemi Srl(阿尔玛系统有限公司);Univ Gustave Eiffel(古斯塔夫·埃菲尔大学);School of Electrical and Computer Engineering, Technical University of Crete(克里特技术大学电气与计算机工程学院);QUBITECH Pc(QUBITECH公司);Institute of High Performance Computing, A*STAR(新加坡科技研究局高性能计算研究所);School of Civil Engineering, National Technical University of Athens(雅典国家技术大学土木工程学院)
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)