Tag
A paper proposing the Task-Aware Diffusion Refiner (TADR), a conditional diffusion model trained against a frozen downstream anomaly detector to fix imputation bias in block-missing IIoT sensor data, improving F1 by 0.338 on SMD while running at 41.4 ms per window on a single CPU core.
提出 LLMMAD，一种基于大语言模型的自回归多模态异常检测框架，用于微服务系统，通过模态专属重建头与预测驱动目标解决跨模态融合和身份捷径问题，并在三个真实数据集上取得最优 F1 提升。
NVIDIA 发布 Minerva，一个面向 AI 工厂的 AIOps 平台，通过整合网络、GPU、存储与工作负载的遥测数据，并利用专用 AI 模型构建动态知识图谱，实现异常检测、故障预测与根因分析，帮助运营团队从被动响应转向主动维护，最大化 GPU 产能与正常运行时间。
AnoMix 提出一种多教师排序蒸馏方法（CoRank），将多个异构无监督时间序列异常检测器蒸馏为单一轻量学生模型（<80k 参数），在七个基准数据集上优于单个检测器和静态分数集成，其零样本变体还能在未见数据集上超越大型时间序列基础模型。
The paper identifies that existing time series tokenization strategies (patch and phase tokenization) introduce spectral distortions such as spectral leakage and aliasing, and proposes TimeFT, a parameter-free, nearly distortion-free frequency-based tokenizer that serves as a drop-in replacement and improves performance across forecasting, classification, and anomaly detection tasks.
The paper proposes WaferHDC, an online open-world wafer defect discovery framework based on hyperdimensional computing that dynamically detects and groups recurring defect patterns without labels or retraining, outperforming the strongest online baseline by 13.3 p.p. in adjusted Rand index on the WM-811K dataset.
BEACON 提出一个融合多模态可观测数据（指标、日志、依赖图）的云系统异常检测框架，通过动态多模态聚合器和异步时空传播器，在三个真实数据集上超越现有最优方法。
VX-One 是一个小型多任务神经网络，输出带类型且经过温度校准的决策基元（校准门控、含显式未知选项的闭集选择、序数分数），用于实时边界流量分诊。论文在 UNSW-NB15、CIC-IDS2017、EMBER2024 上评测其与签名引擎的两阶段级联表现，发现其在时漂移下检测占优，但校准会崩溃且未知攻击拒识能力跨基准迁移性差。
NIST researchers propose a Statistical Ensemble Method (SEM) for radio-frequency jamming detection in O-RAN networks that generalizes across heterogeneous 5G environments, outperforming ML/DL models under distribution shift while supporting cold-start deployment via the Non-RT RIC rApp framework.
NVIDIA researchers propose NV-Tesseract-AD, a curriculum-enhanced conditional diffusion framework with a Transformer backbone for multivariate time-series anomaly detection, achieving ~3.7× F1 improvement over non-curriculum baselines and strong zero-shot transfer to EasyTSAD benchmarks.
提出一种基于轻量级时序Transformer CAN编码器与联邦学习轻量头部的隐私保护框架，用于检测车内网络中的细微时序与上下文异常，无需交换原始CAN数据即可提升共享模型。
The paper presents HydroSphere, a governed data-driven framework for real-time wastewater management combining a TCN-LSTM forecasting model, PPO-based adaptive chemical dosing, and SHADE autoencoder anomaly detection, evaluated on 2.82 million water-quality measurements.
A developer shares AeroTrace-RCA, a flight-sensor root-cause analysis tool built with Claude Code that pairs a local Qwen 2.5 14B model with a strict LLM validator, and reports honest held-out numbers (60% top-1, 20% all-or-nothing) showing the gap between tuned and blind performance.
This CIKM 2026 paper characterizes "convergence collapse" in fixed-target tabular anomaly detectors, where better optimization removes anomaly signal, and proposes Kernel Contraction Matching (KCM), a closed-form kernel-regression detector, plus the Kernel-Anchored Regularizer (KAR) to mitigate collapse and improve AUROC on ADBench.
A structured survey of deep learning–based anomaly detection methods for railway systems, organizing CNNs, RNNs, attention models, autoencoders, GANs, and transformers into a unified taxonomy, and proposing a decision-oriented framework linking anomaly characteristics, data properties, and deployment constraints to detection paradigms including edge–cloud configurations.
This paper studies how much normal evidence (images or categories) is needed to certify a false-alarm-rate-controlled threshold for few-shot industrial anomaly detection. Using a frozen DINOv2 PCA residual ranker on MVTec and VisA, the authors show target-only calibration is shift-fragile, derive lower bounds on the number of iid categories needed for valid distribution-free 95% upper confidence bounds (14–59 draws), and propose the CRESS protocol that largely fails closed with only a few certification categories.
Jevotron is a command-line tool that provides multiple Jev integrations for one-shot anomaly detection on files like CSV, YAML, JSON, and OBO, caching assessments in SQLite and exporting review reports with visible probabilities and evidence.
This paper analyzes failures in reconstruction-based unsupervised learning through geometric conditions and proposes new methods like Dynamic Push and Pull to enhance anomaly detection performance.
This paper introduces a framework using AUC bounds as a differentiable objective for anomaly-free self-optimization of anomaly detection systems, achieving performance gains over conventional model selection methods.
This paper presents Signal2Symbol, a neuro-symbolic framework for explainable anomaly detection in physiological time-series data like ECG and EEG, leveraging symbolic tokenization and temporal reasoning to produce interpretable explanations of anomalous patterns.