# Leveraging Intermediate Representations of Time Series Foundation Models for Anomaly Detection

arXiv: https://arxiv.org/abs/2509.12650 · HTML: https://mlsanity.com/paper/2509.12650/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 16 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [Towards Total Recall in Industrial Anomaly Detection](https://mlsanity.com/paper/2106.08265/) (2021)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Layer by Layer: Uncovering Hidden Representations in Language Models](https://mlsanity.com/paper/2502.02013/) (2025)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder](https://mlsanity.com/paper/1711.00614/) (2017)
- [Sundial: A Family of Highly Capable Time Series Foundation Models](https://mlsanity.com/paper/2502.00816/) (2025)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progress](https://mlsanity.com/paper/2009.13807/) (2020)
- [CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching](https://mlsanity.com/paper/2410.12261/) (2024)
- [TAB: Unified Benchmarking of Time Series Anomaly Detection Methods](https://mlsanity.com/paper/2506.18046/) (2025)
- [AnomalyDINO: Boosting Patch-based Few-shot Anomaly Detection with DINOv2](https://mlsanity.com/paper/2405.14529/) (2024)
- [Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders](https://mlsanity.com/paper/2405.15273/) (2024)
- [Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs](https://mlsanity.com/paper/2502.14830/) (2025)
- [Exploring Representations and Interventions in Time Series Foundation Models](https://mlsanity.com/paper/2409.12915/) (2024)
- [Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction](https://mlsanity.com/paper/2310.15416/) (2023)
- [Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling](https://mlsanity.com/paper/2311.12550/) (2023)
- [Understanding the Inner Workings of Language Models Through Representation Dissimilarity](https://mlsanity.com/paper/2310.14993/) (2023)
- [TimesBERT: A BERT-Style Foundation Model for Time Series Understanding](https://mlsanity.com/paper/2502.21245/) (2025)
- [How do Multimodal Foundation Models Encode Text and Speech? An Analysis of Cross-Lingual and Cross-Modal Representations](https://mlsanity.com/paper/2411.17666/) (2024)
- [Where Do Reasoning Models Refuse?](https://mlsanity.com/paper/2507.03167/) (2025)
- [Decoding Latent Spaces: Assessing the Interpretability of Time Series Foundation Models for Visual Analytics](https://mlsanity.com/paper/2504.20099/) (2025)

## Built on by (most cited first, 1 of 1)

- [Training-Free Human-in-the-Loop Anomaly Detection via Memory Bank Correction](https://mlsanity.com/paper/2608.17775/) (2026)

## Abstract (arXiv)

Detecting anomalies in time series data is essential for the reliable operation of many real-world systems. Recently, time series foundation models (TSFMs) have emerged as a powerful tool for anomaly detection. However, existing methods typically rely on the final layer's representations of TSFMs, computing the anomaly score as a reconstruction or forecasting error via a task-specific head. Instead, we propose TimeRep, a novel anomaly detection approach that leverages the intermediate layer's representations of TSFMs, computing the anomaly score as the distance between these representations. Given a pre-trained TSFM, TimeRep selects the intermediate layer and patch-token position that yield the most informative representation. TimeRep forms a reference collection of intermediate representations from the training data and applies a core-set strategy to reduce its size while maintaining distributional coverage. During inference, TimeRep computes the anomaly score for incoming data by measuring the distance between its intermediate representations and those of the collection. To address concept drift, TimeRep integrates an adaptation mechanism that, at inference time, augments the collection exclusively with non-redundant intermediate representations from incoming data. We conducted extensive experiments on the UCR Anomaly Archive, which contains 250 univariate time series. TimeRep consistently outperforms a broad spectrum of state-of-the-art baselines, including non-DL, DL, and foundation model-based methods.