VACE (Velocity‑Aligned Channel Embeddings) is a self‑supervised anomaly detection method for multivariate time series that learns a geometrically structured representation. It trains a channel‑aware encoder using a velocity‑consistency objective, avoiding negatives and synthetic anomalies, so that normal data form locally smooth, directionally coherent trajectories in embedding space. At inference, VACE combines a Mahalanobis positional score with a directional score that gates the positional score where local dynamics deviate, achieving state‑of‑the‑art performance on the TSB‑AD‑M benchmark.
arXiv:2508. 00909v2 Announce Type: replace Abstract: Time series anomaly detection plays a critical role in a wide range of real-world applications.
Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection introduces OracleAD, an unsupervised framework that encodes each variable’s past into a causal embedding to jointly predict the present and reconstruct the input window. The embeddings are projected via self‑attention into a shared latent space, capturing dynamic spatial relationships that are aligned to a Stable Latent Structure (SLS) representing normal-state relationships. Anomalies are detected through a dual scoring mechanism based on prediction error and deviation from the SLS, allowing fine‑grained diagnosis and root‑cause identification at the variable level.
arXiv:2602. 08638v2 Announce Type: replace-cross Abstract: As a fundamental data mining task, unsupervised time series anomaly detection (TSAD) aims to build a model for identifying abnormal timestamps without assuming the availability of annotations.
LEAP is a new time‑series anomaly detection model that avoids reconstruction by using masked prediction and latent‑embedding evidence. It removes patches from a window, predicts them from remaining context, and scores prediction errors as anomaly evidence. The model incorporates three label‑free novelty signals—latent‑embedding novelty, local temporal contrast, and per‑channel novelty—and achieves strong performance on the TSB‑AD benchmark, with statistically significant gains from each component.
arXiv:2603. 26842v3 Announce Type: replace-cross Abstract: Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems.
arXiv:2604. 13924v3 Announce Type: replace-cross Abstract: 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.
TENET is a Time-point Encoding Network designed for unsupervised multivariate time series anomaly detection. It reframes the task as estimating current-point system-state compatibility by constructing a latent representation of the target time point from variable-level temporal context within an input window. The model uses a temporal layer to retrieve context relative to the current point, encodes time with point-centered embeddings, and adaptively mixes this context with the current representation, then evaluates the latent state with a fixed standard-normal negative log-likelihood score, achieving state-of-the-art performance across benchmark datasets.
LEARN-TS is a method for multivariate time‑series anomaly detection that uses a frozen language model to generate two semantic representations: one that captures window‑specific observation context without exact numerical values, and another that provides a fixed, dataset‑agnostic normality prompt. These representations guide a patch‑masked reconstruction process, allowing the model to estimate normality discrepancy and produce timestamp‑level anomaly evidence. Experiments on four benchmarks show that LEARN‑TS achieves the best mean performance in 13 of 16 dataset‑metric comparisons, and ablation studies confirm the benefits of observation conditioning, joint normality alignment, and semantic references.
This paper introduces IDEAL, a framework for few-shot anomaly detection that uses both normal and anomalous reference examples. IDEAL suppresses irrelevant normal variations and encodes intrinsic deviation vectors that capture discriminative anomaly directions. Experiments on eight real-world datasets show that IDEAL generalizes to unseen anomalies and outperforms existing methods.
The paper investigates whether large language models (LLMs) can serve as feature extractors for zero‑shot multivariate time‑series anomaly detection (MTSAD). By tokenising each time step individually and analysing the separability of the resulting feature spaces, the authors evaluate the representations using an unsupervised Isolation Forest. They also examine whether the performance stems from the LLMs’ language pre‑training or from other factors, providing empirical insights into cross‑modal foundation models for anomaly detection.
DIFFINT is a reconstruction‑based anomaly detector that uses a differentiable autoencoder with a latent bottleneck composed of soft, axis‑aligned interval memberships. Each latent unit represents a human‑readable hyper‑rectangle in feature space, allowing the model to encode how strongly an instance falls inside each interval and to compute reconstruction error as the anomaly score. The method provides a certified lower bound on reconstruction error for points outside all active intervals, a suppression mechanism for sparse abnormalities, and a closed‑form, label‑free importance ranking for each (unit, feature) pair, achieving top performance on 48 ADBench benchmarks against 22 baselines.
The paper introduces NC‑TFAD, a task‑free continual anomaly detection framework that leverages neural‑collapse geometry to learn from non‑stationary data streams without task boundaries. It freezes a pretrained backbone, aligns streaming features to a simplex Equiangular Tight Frame prototype space, and uses synthetic anomaly anchors, inter‑ and intra‑class regularization, and a Focal Neural Collapse Contrastive loss to stabilize representations and enhance normal‑anomaly separability. A normal‑patch‑prototype‑guided localization branch generates calibrated anomaly heatmaps, and extensive experiments on MVTec AD and VisA demonstrate that NC‑TFAD outperforms existing task‑free continual learning and unified anomaly detection baselines in both image‑level detection and pixel‑level localization.