Time Series Analysis and Forecasting

Últimos artículos

• Domain Generalization under Sampling Pattern Shifts in Irregular Time Series

  Changhun Kim, Joohyung Lee, Kwanhyung Lee, Donghwee Yoon, Grigorios Chrysos, Eunho Yang · 29 de septiembre de 2026

  Irregularly sampled multivariate time series (ISMTS) are prevalent in real-world applications, where both observation times and available measurements can vary substantially across domains. While recent models increasingly exploit such sampling information for prediction, its robustness under sampli…

• Rondo: Unsupervised Discovery of Recurring Temporal Structure

  Yingtian Shi, Ankith Chandra, Thomas Pl\"otz · 29 de septiembre de 2026

  Many real-world time series data exhibit structural properties at multiple scales, from short, recurring units to complex sequences composed of these units. Unsupervised discovery of both these components and structure enables the design of intelligent systems that help interpret temporal data, ther…

• TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra

  Weiwei Ye, Renhe Jiang, Hangchen Liu, Dongyuan Li, Yoshihide Sekimoto · 29 de septiembre de 2026

  Real-world time series are inherently non-stationary, with trends, periodic patterns, and uncertainty evolving over time. While the Fourier domain offers a natural lens to model time series, current deep learning approaches do not explicitly model evolution and randomness in the Fourier spectra, whi…

• Does Joint-Embedding Predictive Architecture Pretraining Help Time Series Forecasting?

  Yutong Feng, Bowen Liao, See Kiong Ng, Yuxuan Liang · 29 de septiembre de 2026

  Joint-embedding predictive architectures (JEPA) have emerged as a promising self-supervised pretraining paradigm for time series, learning representations by predicting target embeddings in latent space rather than reconstructing raw signals. Yet evidence on their benefits remains mixed, and most st…

• DrafTS: Time-Aware Decomposition with Residual Correction for Time Series Modeling

  Yiqiu Liu, Siru Zhong, Zhiguang Wang, Qingsong Wen, Yuxuan Liang · 29 de septiembre de 2026

  Real-world time series contain evolving underlying dynamics with irregular variations that lack stable temporal patterns and are often referred to as noise. Existing methods address this mixture by filtering frequencies or suppressing noisy observations. They either miss temporal evolution or risk s…

• ChronoFlow: Hierarchical Flow Matching for Irregular Time Series Generation

  Changhun Kim, Sunguk Jang, Jeongjun Lee, Juhwan Choi, Sangchul Hahn, Grigorios Chrysos, Eunho Yang, Juho Lee · 29 de septiembre de 2026

  Recent advances in generative modeling have substantially improved time series generation, yet most existing methods either assume a regular temporal grid or focus on feature dynamics under a given sampling structure. This makes them illsuited for generating irregular time series in their native for…

• MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off

  Ibram Abdelmalak, Mischa Putzke, Jungmin Choi, Tom Hanika, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme · 29 de septiembre de 2026

  Multivariate Time Series Forecasting (MTSF) models that mix information across channels assume that the past of one channel carries information about the future of another. Yet they are evaluated on a small fixed set of standard datasets whose cross-channel structure is rarely examined. We ask two q…

• Progressive Memory Transformer: Memory-Aware Attention for Time-Series

  Tord Sture Stangeland, Andreas K\"ohler, Steffen M{\ae}land, Ad\'in Ram\'ires Rivera · 28 de septiembre de 2026

  Time-series carry structure simultaneously at multiple scales (fine-grained variation, mid-range motifs, and global properties) and downstream tasks operate at correspondingly different scales. Most existing self-supervised learning approaches supervise representations globally via instance-level co…

• Aurora-X: Built for Extreme Time Series Forecasting

  Xingjian Wu, Chenjuan Guo, Xiangfei Qiu, Zhigang Hu, Hanyin Cheng, Peng Chen, Yang Shu, Jilin Hu, Bin Yang · 28 de septiembre de 2026

  Time series foundation models (TSFMs) enable cross-domain forecasting, but their development as general-purpose forecasters remains constrained by underexplored training potential and limited architectural versatility. To address these challenges, we introduce Aurora-X, a billion-scale TSFM with a p…

• SwitchPFN: Shared Switching Dynamics for Frozen In-Context Time Series Classification

  Zhenyi Zhu, Jacqueline Pang, Peilin Shen, Tianyi Song, Tingwei Zhang, Keyi Hu, Kangjun Yin, Shiwei Pu, Yingbo Zhou, Chen Shao · 25 de septiembre de 2026

  Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are converted into tabular representations. Existing representations face two challenges: global aggregation can lose the order of temporal evolution, whil…

• TimeBraid: Unifying Time Series and Language for Understanding and Forecasting

  Xinyue Wang, Jiacheng Pang, Kun Zhou, Kexin Zhang, Defu Cao, Fan Feng, Faisal, Songyao Jin, Yan Liu, Biwei Huang · 25 de septiembre de 2026

  We present TimeBraid, a series of unified time-series and language models that align pretrained language models and pretrained time-series foundation models through interleaved global residual attention layers. Each model inherits knowledge, instruction following, and reasoning from one side, contin…

• Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting

  Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu · 25 de septiembre de 2026

  Time series analysis is fundamental in domains such as finance, healthcare, and meteorology. Real-world time series often exhibit multiscale characteristics shaped by diverse latent factors, resulting in intricate temporal patterns and rich frequency structures. However, existing approaches typicall…

• TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent

  Jie Yang, Yan Zheng, Jiarui Sun, Xiran Fan, Junpeng Wang, Liang Wang, Zelin Xu, Qinghua Liu, Zhengyu Fang, Yiwei Cai, Philip S. Yu · 24 de septiembre de 2026

  Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However, we identify two failures in this setup. Human-Agent Tool Misalignment: a library of 21 expert-curated tools helps on some tasks and hurts on other…

• Learning Where to Look: A Shared Relative-Alignment Module for Time-Series Forecasting and PPG-to-Vital-Sign Reconstruction

  Ragamayi Puli, Shunya Nagashima · 24 de septiembre de 2026

  PPG-to-vital-sign reconstruction turns a wrist-worn photoplethysmogram into clinical waveforms such as the ECG. Long-horizon multivariate time-series forecasting underpins planning in energy, weather, and traffic. Both generate a target sequence from a condition sequence, and current models hard-cod…

• Spatiotemporal Kronecker Covariance Neural Networks

  Andrea Cavallo, Athanasios Georgoutsos, Elvin Isufi · 23 de septiembre de 2026

  Multivariate time series contain complex patterns that span across both space and time. While covariance-based statistical tools like spatiotemporal Principal Component Analysis (ST-PCA) help identify these patterns, they are limited to linear operations and prone to estimation errors with limited d…

• TimeInteract: Towards Real-Time Interactive Intelligence for Streaming Time Series

  Sheng Pan, Yongli Gu, Yiqing Guo, Warren Jin, Bo Du, Shirui Pan, Ming Jin · 23 de septiembre de 2026

  Real-world time series evolve continuously, with meaningful changes potentially emerging at any moment. However, existing time-series language models (TSLMs) remain inherently static. They either receive complete sequences for offline processing or alternate between streaming input and response gene…

• Overlay\_dx - Automating forecasting evaluation

  Long Ngo, Mohammed Amine Chamli, Jonathan Rivalan, Thomas Jaillon · 22 de septiembre de 2026

  Traditional evaluation metrics provides numerical values but often lack comprehensibility, hindering effective differentiation of model performances. Our work addresses this challenge by introducing overlay\_dx, a novel evaluation metric measuring the performance of time series prediction models. Ov…

• MUSE: Dependency-Aware Adaptation of a Frozen Vision Backbone for Multivariate Time Series Forecasting

  Xinying Cai, Junkai Lu, Yuhan Zhu, Xiaoyun Yu, Xiangfei Qiu, Jilin Hu · 22 de septiembre de 2026

  Multivariate time-series forecasting is essential to many real-world applications. Recent large vision models (LVMs) offer a promising paradigm by transferring cross-domain visual priors to time-series forecasting. However, existing LVM-based methods face two key challenges: balancing independent vi…

• ShapeLex: Decoupling Local Shape Symbolization and Global Scale Modeling for Text-Controlled Time Series Generation

  Subo Wei, Jianqi Gao, Mingyan Fan, Shaorong Xie, Xinzhi Wang, Yongpeng Dong · 22 de septiembre de 2026

  Text-controlled time series generation aims to synthesize sequences that follow natural-language descriptions while remaining faithful to real data distributions. Existing paradigms often couple semantic understanding and sequence modeling in a single continuous latent space, lacking explicit local …

• One Patch, Three Roles: What Is Actually Coupled in Autoregressive Time-Series Forecasting?

  Ziang Li, Yue Huang, Guoxu Zhou, Na Han, Jie Wen, Lunke Fei, Xiaozhao Fang · 22 de septiembre de 2026

  Patch-based autoregressive time-series forecasting often ties input representation, learned transitions, and recursive execution to one patch length. We ask which of these roles can be adjusted separately. A supporting atomic-encoding study finds greater sensitivity to model width than to atom group…

• A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting

  Zhihao Lin, Li Lin, Qi Zhang, Kaiwen Xia, Shuai Wang, Jialin Qiao · 22 de septiembre de 2026

  Time series foundation models (TSFMs) have recently delivered impressive zero-shot performance across diverse forecasting tasks. However, real-world decision-making frequently relies on \emph{irregular multivariate time series} (IMTS), where inconsistent inter-observation intervals and asynchronous …

• A Synthetic Multivariate Refrigerator Time-Series Dataset for Predictive Maintenance

  Islam Benamirouche, Feriel Fass, Djemel Ziou · 22 de septiembre de 2026

  We generated synthetic multivariate time series for 27 refrigerators with a simplified physicsinspired simulator at one-minute resolution. The simulator includes ambient-temperature variation, door use, thermostat and compressor operation, heat exchange, defrost, electrical consumption, and six prog…

• SegTSim: A Big Data Driven Segmented Temporal Simulation Framework for Heterogeneous Multivariate Systems

  Xinhang Li, Chenxi Geng, Yujia Sun · 22 de septiembre de 2026

  Heterogeneous multivariate time-series systems exhibit segment-specific nonlinear dynamics that challenge monolithic forecasting architectures. We propose SegTSim, a big-data-driven segmented temporal simulation framework that integrates segment-specific elasticity modeling with adaptive min-gating,…

• Unlocking Pretrained Vision Transformers for Time Series Classification

  Simon Roschmann, Quentin Bouniot, Vasilii Feofanov, Ievgen Redko, Zeynep Akata · 22 de septiembre de 2026

  Adapting vision models for time series analysis is compelling, yet all existing approaches are falling short of dedicated time series foundation models (TSFMs) in classification. In this work, we propose Time Vision Transformer (TiViT), the first framework that successfully unlocks the representatio…

• TAC-Time: Texts as Channels For Multimodal Time Series Forecasting

  Jiayi Liang, Xiaotian Gu, Xinyu Xie, Yuanbin Wu, Xiaoling Wang · 22 de septiembre de 2026

  Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recent multimodal approaches attempt to incorporate textual signals, but they often treat text as static features or use large language models as forecas…