arXiv Machine Learning August 4, 2026 By Seunghan Lee, Jaehoon Lee, Jun Seo, Junhyeok Kang, Sangjun Han, Sungdong Yoo, Minjae Kim, Tae Yoon Lim, Dongwan Kang, Hwanil Choi, Soonyoung Lee, Wonbin Ahn

Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting

Read the original on arXiv Machine Learning →

arXiv:2608. 01857v1 Announce Type: new Abstract: The direction of change --- whether a series will move up or down --- is often as important as its exact value in decisiondriven applications such as risk management and financial forecasting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 10

Not All Variables Agree: Reliability-Aware Variable-Wise Gradient Surgery for Multivariate Time-Series Forecasting

arXiv:2609.08554v1 Announce Type: new Abstract: In data-driven training, multivariate time-series forecasting is usually optimized with a scalar loss averaged over samples, variables, and horizons. T...

By Jinwoo Park, Hyeongwon Kang, Pilsung Kang

arXiv Machine Learning

Jun 4

Post-Training Corrections for Improved Time-Series Forecasting

arXiv:2505. 15354v3 Announce Type: replace Abstract: Time-series forecasting is a critical task in various business domains, but it remains inherently challenging.

By Hamza Cherkaoui, Malik Tiomoko, Giuseppe Paolo, Zhang Yili, Yu Meng, Zhang Keli, Hafiz Tiomoko Ali

benchmarks

arXiv AI

4d ago

Loss-Guided Pretraining Data Selection for Time-Series Foundation Models

arXiv:2609.37255v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) are pretrained on heterogeneous collections containing billions of observations, yet their training windows are...

By Yike Li, Shaoxu Song, Jianmin Wang

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

4d ago

Volatility-Clustering Adaptation for Financial Time Series

arXiv:2609.37715v1 Announce Type: new Abstract: Time-series foundation models are increasingly adapted to new domains through fine-tuning on target data, under the implicit assumption that more targe...

By Manh Nguyen, Minh Hoang Nguyen, Huu Hiep Nguyen, Van Dai Do, Hung Le

fine-tuning

arXiv Machine Learning

Sep 3

Compositional Spectral Prompts for LLM-based Online Time Series Forecasting

The paper introduces CoSPOT, an online time series forecasting framework that uses a frozen pre‑trained large language model (LLM) as the core forecaster. CoSPOT adapts to evolving data by applying compositional spectral prompts—frequency‑domain basis prompts weighted by their amplitudes—allowing the model to represent unseen patterns as new combinations of learned bases while updating few parameters. Experiments on real‑world datasets show CoSPOT’s effectiveness in extended online phases and cross‑dataset scenarios with significant distribution shifts.

By Seungyoon Choi, Hyunchul Kim, Jae-Gil Lee, Chanyoung Park

llms

One email a morning, machine-written

Related stories

Not All Variables Agree: Reliability-Aware Variable-Wise Gradient Surgery for Multivariate Time-Series Forecasting

Post-Training Corrections for Improved Time-Series Forecasting

Loss-Guided Pretraining Data Selection for Time-Series Foundation Models

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

Volatility-Clustering Adaptation for Financial Time Series

Compositional Spectral Prompts for LLM-based Online Time Series Forecasting