arXiv Machine Learning June 10, 2026 By Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers, M. M. Lutfe Elahi, Sifat Momen, Nabeel Mohammed, Shafin Rahman

One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data

Read the original on arXiv Machine Learning →

arXiv:2606. 10678v1 Announce Type: new Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 11

CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting

arXiv:2511. 09789v2 Announce Type: replace Abstract: Recent advances in deep forecasting models have achieved remarkable performance, yet most approaches still struggle to provide both accurate predictions and interpretable insights into temporal dynamics.

By Fulong Yao, Wanqing Zhao, Chao Zheng, Xiaofei Han

llms benchmarks

arXiv Machine Learning

Jul 2

StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting

arXiv:2607. 00197v1 Announce Type: new Abstract: Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation.

By Haroon Gharwi, Yue Dai, Kai Shu

llms benchmarks

arXiv AI

Jun 16

FlowState: Sampling-Rate-Equivariant Time-Series Forecasting

arXiv:2508. 05287v3 Announce Type: replace-cross Abstract: Existing time series foundation models (TSFMs), often based on transformer variants, lack adaptability to different sampling rates, struggle with generalization across varying context and target lengths, and are computationally inefficient.

By Lars Graf, Thomas Ortner, Stanis{\l}aw Wo\'zniak, Angeliki Pantazi

llms benchmarks

arXiv Machine Learning

Aug 4

AROpt: An Optimization Method for Autoregressive Time Series Forecasting

arXiv:2602. 02288v3 Announce Type: replace Abstract: Current time-series forecasting models are primarily based on transformer-style neural networks.

By Zheng Li, Jerry Cheng, Huanying Gu

llms benchmarks

arXiv Machine Learning

Jul 31

Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework

arXiv:2607. 28035v1 Announce Type: new Abstract: Irregular multivariate time series are widely encountered in applications such as healthcare monitoring, human activity recognition, and environmental sensing.

By Tianen Shen, Zhengyu Li, Yutong Li, Xiangfei Qiu, Xingjian Wu, Bin Yang, Jilin Hu

llms diffusion nlp benchmarks

arXiv AI

Jun 10

CITRAS: Covariate-Informed Transformer for Time Series Forecasting

arXiv:2503. 24007v4 Announce Type: replace-cross Abstract: In time series forecasting, covariates represent external factors that influence target variables.

By Yosuke Yamaguchi, Issei Suemitsu, Wenpeng Wei

llms

Related stories

CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting

StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting

FlowState: Sampling-Rate-Equivariant Time-Series Forecasting

AROpt: An Optimization Method for Autoregressive Time Series Forecasting

Enhancing Irregular Time Series Forecasting with Continuous-Time Modeling Framework

CITRAS: Covariate-Informed Transformer for Time Series Forecasting