The paper introduces Wavelet Flow Matching, a method for generating multivariate time series by applying flow matching to multilevel discrete wavelet coefficients. By working in the wavelet domain, the model captures coarse-to-fine temporal structure implicitly and uses a channel-token transformer to model cross-channel dependencies. Experiments on seven benchmark datasets and four sequence lengths show that the approach matches or surpasses existing methods, especially in Context-FID and discriminative score metrics.
By Lucas Poinsignon, Jorge da Silva Gon\c{c}alves, Samuel Ruip\'erez-Campillo, Julia E. Vogt
arXiv:2608. 09193v1 Announce Type: cross Abstract: Unsupervised time-series domain adaptation (DA) addresses the challenge of transferring a classifier from a labeled source domain to an unlabeled target domain under distribution shifts induced by different users, sensors, devices, acquisition conditions, or temporal dynamics.
By Felix Ott, Christopher Mutschler
arXiv:2506.08641v3 Announce Type: replace
Abstract: Adapting vision models for time series analysis is compelling, yet all existing approaches are falling short of dedicated time series foundation mo...
By Simon Roschmann, Quentin Bouniot, Vasilii Feofanov, Ievgen Redko, Zeynep Akata
The paper introduces m-WCN, an end‑to‑end deep learning framework that neuralizes multi‑wavelet decomposition to jointly extract temporal patterns and frequency components from time series. Two task‑specific architectures built on m‑WCN—TFBC for classification and FTB for forecasting—are shown to outperform baseline models on 64 UCR datasets and seven forecasting benchmarks, achieving average improvements of nearly 20% in both tasks. The approach leverages trainable convolutional operators and orthogonality constraints to produce interpretable multi‑resolution representations.
By Xiaohan Jiang, Jingyuan Wang, Jiahao Ji, Yongyao Wang, Chen Yang, Junjie Wu
arXiv:2608. 09091v1 Announce Type: cross Abstract: Transfer learning is particularly useful in settings with limited training data, and within image classification it is common to transfer learn upon massive datasets like ImageNet , CIFAR-100, or COCO .
By Jing Ning, James D. Braza
WinoTS introduces a wavelet‑based self‑distillation framework for time‑series models that uses time‑frequency augmentations to create multi‑scale structural views, avoiding distortion of signal dynamics. The method outperforms state‑of‑the‑art baselines in long‑term forecasting, cross‑domain zero‑shot transfer, and unsupervised anomaly detection, and linear probing on frozen representations often beats fully supervised training from scratch. Ablation studies show WinoTS is architecture‑agnostic and demonstrates that time‑frequency transformations offer a principled alternative to vision‑style spatial augmentations.
By Noam Major, Kathy Razmadze, Yoli Shavit
arXiv:2601.20845v2 Announce Type: replace
Abstract: Time series forecasting is a fundamental problem with applications in climate, energy, healthcare, and finance. Many existing approaches require do...
By Olaf Yunus Laitinen Imanov, Derya Umut Kulali, Taner Yilmaz
SMart is a new time series representation learning framework that combines a multi-phase recurrence plot recovery task with a source dataset selector. The recovery task uses three alternative modes to guide the encoder in capturing time series dynamics, while the selector chooses multiple suitable source datasets to augment the target dataset during pre‑training. Experiments demonstrate that SMart surpasses state‑of‑the‑art models, reducing mean absolute error by up to 19.5% in regression and increasing classification accuracy by up to 1.34%.
By Fang He, Wang-chien Lee
The paper introduces a spectrally-aligned latent-flow model for time‑series generation that trains the latent space to preserve dynamical properties relevant to synthetic data quality. By incorporating fine‑tuning losses based on Fourier, wavelet, and signature transforms, the method mitigates spectral mismatches caused by latent compression and ensures alignment with true signals in terms of smoothness and targeted spectral content. Experiments on real‑world long‑range univariate and multivariate benchmarks show that the aligned model outperforms a base latent‑flow model and state‑of‑the‑art approaches in signal realism, computational efficiency, and local structure alignment.
By Camilo Carvajal Reyes, Felipe Tobar
arXiv:2602. 01359v3 Announce Type: replace-cross Abstract: Although recent studies on time-series anomaly detection have increasingly adopted ever-larger neural network architectures such as transformers and foundation models, they incur high computational costs and memory usage, making them impractical for real-time and resource-constrained scenarios.
By Jinju Park, Seokho Kang
The paper introduces m-WCN, an end‑to‑end deep learning framework that neuralizes multi‑wavelet decomposition to jointly extract temporal patterns and frequency components from time series. It enforces orthogonality constraints to produce interpretable multi‑resolution representations, and builds two task‑specific architectures—TFBC for classification and FTB for forecasting—on top of this foundation. Experiments on 64 UCR datasets and seven forecasting benchmarks show that TFBC and FTB outperform baseline models, achieving average improvements of about 20% in both classification and forecasting tasks.
arXiv:2607. 06796v1 Announce Type: cross Abstract: Deep learning has achieved remarkable success in various domains including time series analysis, computer vision and natural language processing.
By Javidan Abdullayev, Maxime Devanne, Jonathan Weber, Germain Forestier