10 papers
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
Junru Zhang, Lang Feng, Jinbo Wang +6
Generating high-quality time-series data is challenging because real-world signals often exhibit multimodal patterns and multiscale dynamics, including oscillations and high-freque…
SDFlow: Similarity-Driven Flow Matching for Time Series Generation
Wei Li, Shibo Feng, Pengcheng Wu +3
Vector quantization (VQ) with autoregressive (AR) token modeling is a widely adopted and highly competitive paradigm for time-series generation. However, such models are fundamenta…
A Unified Shape-Aware Foundation Model for Time Series Classification
Zhen Liu, Yucheng Wang, Boyuan Li +4
Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundatio…
Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
Sachith Abeywickrama, Emadeldeen Eldele, Min Wu +2
Patch-based transformers have emerged as efficient and improved long-horizon modeling architectures for time series modeling. Yet, existing approaches rely on temporally-agnostic p…
Adapting LLMs to Time Series Forecasting via Temporal Heterogeneity Modeling and Representation Alignment
Yanru Sun, Emadeldeen Eldele, Zongxia Xie +5
Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural language tasks…
Learning Soft Sparse Shapes for Efficient Time-Series Classification
Zhen Liu, Yicheng Luo, Boyuan Li +3
Shapelets are discriminative subsequences (or shapes) with high interpretability in time series classification. Due to the time-intensive nature of shapelet discovery, existing sha…
Bridging Distribution Gaps in Time Series Foundation Model Pretraining with Prototype-Guided Normalization
Peiliang Gong, Emadeldeen Eldele, Min Wu +3
Foundation models have achieved remarkable success across diverse machine-learning domains through large-scale pretraining on large, diverse datasets. However, pretraining on such…
Retrieving Filter Spectra in CNN for Explainable Sleep Stage Classification
Stephan Goerttler, Yucheng Wang, Fei He +1
Despite significant advances in deep learning-based sleep stage classification, the clinical adoption of automatic classification models remains slow. One key challenge is the lack…
Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
Yanru Sun, Zongxia Xie, Emadeldeen Eldele +3
Time series forecasting, which aims to predict future values based on historical data, has garnered significant attention due to its broad range of applications. However, real-worl…
Explaining Time Series via Contrastive and Locally Sparse Perturbations
Zichuan Liu, Yingying Zhang, Tianchun Wang +8
Explaining multivariate time series is a compound challenge, as it requires identifying important locations in the time series and matching complex temporal patterns. Although prev…