mlsanityData to 14 Oct 2026

ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection

arXiv 2604.13924 ↗First posted 15 Apr 2026cs.LG cs.AI cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous anomalies and the scarcity of labelled data. This scarcity makes unsupervised approaches predominant, yet existing methods often rely on reconstruction or forecasting, which struggle with complex data, or on embedding-based approaches that require domain-specific anomaly synthesis and fixed distance metrics. We propose ASTER, a framework that generates pseudo-anomalies directly in the latent space, avoiding handcrafted anomaly injections and the need for domain expertise. A latent-space decoder produces tailored pseudo-anomalies to train a Transformer-based anomaly classifier, while a pre-trained LLM enriches the temporal and contextual representations of this space. Experiments on three benchmark datasets show that ASTER achieves state-of-the-art performance and sets a new standard for LLM-based TSAD.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 73 references that are in the map. First posted on arXiv 15 Apr 2026.

Builds on

42 of 73 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
  7. 2022TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysiscited by 1,058
  8. 2024Chronos: Learning the Language of Time Seriescited by 759
  9. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 700
  10. 2023A decoder-only foundation model for time-series forecastingcited by 692
  11. 2024KAN: Kolmogorov-Arnold Networkscited by 649
  12. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 632
30 more
  1. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 482
  2. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  3. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  4. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 214
  5. 2024Timer: Generative Pre-trained Transformers Are Large Time Series Modelscited by 208
  6. 2023TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Seriescited by 169
  7. 2024Are Language Models Actually Useful for Time Series Forecasting?cited by 168
  8. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 151
  9. 2023UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecastingcited by 144
  10. 2023LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasterscited by 129
  11. 2023Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Studycited by 116
  12. 2018Adversarially Learned Anomaly Detectioncited by 115
  13. 2024CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuningcited by 108
  14. 2024ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoningcited by 103
  15. 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 97
  16. 2024CAD-Recode: Reverse Engineering CAD Code from Point Cloudscited by 66
  17. 2025TAB: Unified Benchmarking of Time Series Anomaly Detection Methodscited by 60
  18. 2024Can LLMs Understand Time Series Anomalies?cited by 41
  19. 2023ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detectioncited by 40
  20. 2016Multivariate Industrial Time Series with Cyber-Attack Simulation: Fault Detection Using an LSTM-based Predictive Data Modelcited by 34
  21. 2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
  22. 2024Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detectioncited by 26
  23. 2021Merlion: A Machine Learning Library for Time Seriescited by 25
  24. 2023CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detectioncited by 15
  25. 2023Explainable Time Series Anomaly Detection using Masked Latent Generative Modelingcited by 15
  26. 2024LLM-Mixer: Multiscale Mixing in LLMs for Time Series Forecastingcited by 8
  27. 2025GenIAS: Generator for Instantiating Anomalies in time Seriescited by 4
  28. 2025MADLLM: Multivariate Anomaly Detection via Pre-trained LLMscited by 3
  29. 2025Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbationcited by 2
  30. 2025L-GTA: Latent Generative Modeling for Time Series Augmentationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026An Insight on Evaluation Metrics Under the Imbalanced Case of Anomaly Detectioncited by 0