mlsanityData to 14 Oct 2026

FreSia: Frequency-Semantic Instantiation and Alignment for Multivariate Time Series Analysis

arXiv 2610.05726 ↗First posted 5 Oct 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Large Language Models (LLMs) have shown strong potential in multivariate time series forecasting and anomaly detection. Existing studies predominantly inject temporal information into LLMs via direct numerical tokenization or heuristic textual descriptions. However, LLMs still face difficulty in perceiving the underlying structural patterns of numerical time series, particularly the seasonal and trend components obscured by discrete numerical tokens. To bridge this gap, we propose FreSia, a frequency-aware framework that establishes an effective alignment between the semantic space of LLMs and the frequency space of time series. Specifically, FGPrompt, a Frequency-Guided Prompt mechanism within FreSia, distills the frequency-domain structures of time series and projects them into prompts tailored to the semantic space of LLMs. Furthermore, we introduce a Global-driven Context Learning (GCL) component, which uses a global CLS-driven probe to generate global context to bridge the time-frequency domain gap and fuse the multi-modal information. Experiments on eight forecasting benchmarks show that FreSia achieves average improvements of 13.48% and 8.06% in MSE and MAE, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 47 references that are in the map. First posted on arXiv 5 Oct 2026.

Builds on

35 of 47 references.

References · 35

  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  2. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
  5. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  6. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  7. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  8. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  9. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
  10. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  11. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 394
  12. 2022Less Is More: Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP Structurescited by 160
23 more
  1. 2023UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecastingcited by 144
  2. 2023LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasterscited by 129
  3. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 127
  4. 2024TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignmentcited by 103
  5. 2024ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Datacited by 100
  6. 2023Segment Any Anomaly without Training via Hybrid Prompt Regularizationcited by 60
  7. 2024FilterNet: Harnessing Frequency Filters for Time Series Forecastingcited by 47
  8. 2024Fredformer: Frequency Debiased Transformer for Time Series Forecastingcited by 45
  9. 2025Context-Alignment: Activating and Enhancing LLM Capabilities in Time Seriescited by 39
  10. 2025TimeCAP: Learning to Contextualize, Augment, and Predict Time Series Events with Large Language Model Agentscited by 37
  11. 2025ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Datasetcited by 37
  12. 2024How Can Large Language Models Understand Spatial-Temporal Data?cited by 33
  13. 2025TimeKAN: KAN-based Frequency Decomposition Learning Architecture for Long-term Time Series Forecastingcited by 30
  14. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 29
  15. 2024Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspectivecited by 26
  16. 2025LangTime: A Language-Guided Unified Model for Time Series Forecasting with Proximal Policy Optimizationcited by 22
  17. 2024Graph Mixture of Experts and Memory-augmented Routers for Multivariate Time Series Anomaly Detectioncited by 20
  18. 2025GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causalitycited by 12
  19. 2025SEMPO: Lightweight Foundation Models for Time Series Forecastingcited by 7
  20. 2025ReFocus: Reinforcing Mid-Frequency and Key-Frequency Modeling for Multivariate Time Series Forecastingcited by 6
  21. 2024TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detectioncited by 5
  22. 2025Visual Anomaly Detection under Complex View-Illumination Interplay: A Large-Scale Benchmarkcited by 4
  23. 2026TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detectioncited by 1

Built on by

Not cited yet.