mlsanityData to 7 Oct 2026

ViTs: Teaching Machines to See Time Series Anomalies Like Human Experts

arXiv 2510.04710 ↗First posted 6 Oct 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Web service administrators must ensure the stability of multiple systems by promptly detecting anomalies in Key Performance Indicators (KPIs). Achieving the goal of "train once, infer across scenarios" remains a fundamental challenge for time series anomaly detection models. Beyond improving zero-shot generalization, such models must also flexibly handle sequences of varying lengths during inference, ranging from one hour to one week, without retraining. Conventional approaches rely on sliding-window encoding and self-supervised learning, which restrict inference to fixed-length inputs. Large Language Models (LLMs) have demonstrated remarkable zero-shot capabilities across general domains. However, when applied to time series data, they face inherent limitations due to context length. To address this issue, we propose ViTs, a Vision-Language Model (VLM)-based framework that converts time series curves into visual representations. By rescaling time series images, temporal dependencies are preserved while maintaining a consistent input size, thereby enabling efficient processing of arbitrarily long sequences without context constraints. Training VLMs for this purpose introduces unique challenges, primarily due to the scarcity of aligned time series image-text data. To overcome this, we employ an evolutionary algorithm to automatically generate thousands of high-quality image-text pairs and design a three-stage training pipeline consisting of: (1) time series knowledge injection, (2) anomaly detection enhancement, and (3) anomaly reasoning refinement. Extensive experiments demonstrate that ViTs substantially enhance the ability of VLMs to understand and detect anomalies in time series data. All datasets and code will be publicly released at: https://anonymous.4open.science/r/ViTs-C484/.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 37 references that are in the map. First posted on arXiv 6 Oct 2025.

Builds on

26 of 37 references.

References · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  5. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,030
  6. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  7. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  8. 2022Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistencycited by 246
  9. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  10. 2023FITS: Modeling Time Series with 10k Parameterscited by 185
  11. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 163
  12. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
14 more
  1. 2024TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignmentcited by 97
  2. 2024ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoningcited by 95
  3. 2024From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflectioncited by 93
  4. 2024ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Datacited by 92
  5. 2023Temporal Data Meets LLM -- Explainable Financial Time Series Forecastingcited by 77
  6. 2024AutoTimes: Autoregressive Time Series Forecasters via Large Language Modelscited by 63
  7. 2025Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysiscited by 32
  8. 2024Large language models can be zero-shot anomaly detectors for time series?cited by 30
  9. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 26
  10. 2024Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspectivecited by 22
  11. 2024TimeSeriesBench: An Industrial-Grade Benchmark for Time Series Anomaly Detection Modelscited by 22
  12. 2022Constructing Large-Scale Real-World Benchmark Datasets for AIOpscited by 19
  13. 2024Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalizationcited by 12
  14. 2025Can Multimodal LLMs Perform Time Series Anomaly Detection?cited by 11

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Harnessing Vision-Language Models for Time Series Anomaly Detection
  2. 2026Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection
  3. 2025Harnessing Vision Models for Time Series Analysis: A Survey
  4. 2024On the Feasibility of Vision-Language Models for Time-Series Classification
  5. 2025MLLM4TS: Leveraging Vision and Multimodal Language Models for General Time-Series Analysis
  6. 2024Can LLMs Understand Time Series Anomalies?
  7. 2024Towards Time Series Reasoning with LLMs
  8. 2024Can LLMs Serve As Time Series Anomaly Detectors?