Latest Anomaly Detection Research Papers

The newest Anomaly Detection papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Anomaly Detection so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
  Tong Xie, Yuanhao Ban, Yunqi Hong, Sohyun An et al. · arXiv · Jun 9, 2026

  Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-unique, noisy, or misaligned with the model prior. Strictly fitting toward this one-hot targe…

• OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib
  Abhijoy Sarkar, Aarchi Singh Thakur · arXiv · Jun 9, 2026

  Resistance to first-line osimertinib in EGFR-mutant non-small-cell lung cancer (NSCLC) is the canonical example of predictable clonal evolution under therapeutic pressure, yet no public benchmark exists for training or evaluating computatio…

• DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals
  Yidan Shen, Neville Mathew, Maham Rahimi, Deependra Dhakal et al. · arXiv · Jun 9, 2026

  Blood pressure (BP) is a key marker for cardiovascular risk assessment and therapeutic decision-making, and Photoplethysmography (PPG) enables low-cost, wearable-friendly cuffless BP estimation. However, even with recent progress, many PPG-…

• Difference-Aware Retrieval Policies for Imitation Learning
  Quinn Pfeifer, Ethan Pronovost, Paarth Shah, Khimya Khetarpal et al. · arXiv · Jun 8, 2026

  Parametric imitation learning via behavior cloning can suffer from poor generalization to out-of-distribution states due to compounding errors during deployment. We show that reusing the training data during inference via a semi-parametric …

• How abundant are good interpolators?
  August Y. Chen, Ahmed El Alaoui · arXiv · Jun 4, 2026

  Let $S$ be the set of unit norm linear classifiers $θ\in \mathbb{R}^d$ which correctly classify every point of a labeled dataset $(X_i,y_i)_{i=1}^n$, $X_i \in \mathbb{R}^d$, $y_i \in \{-1,+1\}$, with a possibly negative margin $κ$ fixed in …

• Drifting Preference Optimization for One-Step Generative Models
  Zhou Jiang, Yandong Wen, Zhen Liu · arXiv · Jun 1, 2026

  One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denois…

• When, why, and how do diffusion posterior samplers fail? A finite-sample lens
  Benjamin A. Burns, Sara Fridovich-Keil · arXiv · May 28, 2026

  Diffusion models have excellent capacity to model complex distributions of natural data, which has made them a popular and effective choice for posterior sampling in imaging inverse problems. Existing methods can incorporate any measurement…

• SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?
  Sy-Tuyen Ho, Minghui Liu, Huy Nghiem, Furong Huang · arXiv · May 28, 2026

  Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck: whether Large Language M…

• Digitally enriching a screening population for pancreatic cancer using routine blood-based measures and clinical histories
  Chris Varghese, Leo Y. Li-Han, Richa Bisht, Ellen Larson et al. · arXiv · May 28, 2026

  Earlier detection of pancreatic cancer is key to enabling wider access to curative treatment and reducing cancer deaths; however, screening is presently not viable. Latent indicators of pathology are evident in an individual's disease and b…

• OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction
  Xin Wang, Linxin Xiao, Yang Yao, Wenwu Zhu · arXiv · May 28, 2026

  Drug synergy prediction (DSP) aims to identify efficacious drug combinations under various cellular contexts with different targets. However, the continual emergence of novel compounds results in variations in molecular scaffolds and sizes,…

• Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning
  Sridhar Mahadevan · arXiv · May 26, 2026

  We propose Kan Extension Transformers (KETs) as a unifying categorical framework for a diverse group of Transformer implementations. The core claim is that a Transformer layer can be viewed as a weighted structured extension operator: stand…

• G <scp>lassbox</scp> AD: An Interactive System for Dissecting Hierarchical Time-Series Anomaly Detection
  Mingyi Huang, Q Liu, Paul Boniol, John Paparrizos · OpenAlex · May 26, 2026

  Time-series anomaly detection (TSAD) is challenging in unsupervised settings because anomalies are heterogeneous and often manifest at different temporal scales. HYDRA addresses this by constructing a multi-level hierarchy of representative…

• Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark
  Xu Yao, Siyuan Zhou, Wu Zhenbo, Chaochuan Hou et al. · arXiv · May 25, 2026

  Weakly supervised anomaly detection (WSAD) has developed in three primary directions: incomplete, inexact, and inaccurate supervision. However, these directions remain isolated, lacking a unified framework to assess whether they address uni…

• Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
  Zixin Jessie Chen, Zhuo Chen, Archer Wang, Jeff Gore et al. · arXiv · May 25, 2026

  Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce $\text…

• Retrieval-Augmented Detection of Potentially Abusive Clauses in Chilean Terms of Service
  Christoffer Loeffler, Tomás Rey Pizarro, Daniel Ignacio Miranda Vásquez, Andrea Martínez Freile · arXiv · May 25, 2026

  Online Terms of Service often function as contracts of adhesion, creating asymmetries that may expose consumers to potentially abusive clauses. In Chile, assessing such clauses is legally challenging because some provisions clearly violate …

• FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection
  Huanchi Wang, Zihang Huang, Yifang Tian, Kristina Dzeparoska et al. · arXiv · May 21, 2026

  Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the specific message responsible. This coarse granularity forces op…

• Cyber-Physical Anomaly Detection in IoT-Enabled Smart Grids Using Machine Learning and Metaheuristic Feature Optimization
  Adis Alihodžić, Eva Tuba, Milan Tuba · arXiv · May 21, 2026

  Modern smart grids rely on dense measurement infrastructures, communication links, and intelligent field devices. Although this improves supervision and control, it also increases vulnerability to cyber-physical disruptions. Operators must …

• Learning Normal Representations for Blood Biomarkers
  Aashna P. Shah, Michelle M. Li, Yash Lal, Seffi Cohen et al. · arXiv · May 18, 2026

  Blood-based biomarkers underpin clinical diagnosis and management, yet their interpretation relies largely on fixed population reference intervals that ignore stable, intra-patient variability. As such, population-based interpretation can m…

• Learning Quantifiable Visual Explanations Without Ground-Truth
  Amritpal Singh, Andrey Barsky, Mohamed Ali Souibgui, Ernest Valveny et al. · arXiv · May 18, 2026

  Explainable AI (XAI) techniques are increasingly important for the validation and responsible use of modern deep learning models, but are difficult to evaluate due to the lack of good ground-truth to compare against. We propose a framework …

• HYDRA: A Multi-Level Hierarchy-Driven Approach for Robust Anomaly Detection in Time Series
  Mingyi Huang, Qinghua Liu, Paul Boniol, John Paparrizos · Proceedings of the ACM on M... · May 18, 2026

  Time-series anomaly detection is critical across various domains. Despite advances in neural networks and foundation models, recent studies show that traditional data mining methods remain highly competitive due to their effectiveness and s…

• The Ma Resonance Theory v2.0: Neutrinos as Indicators of Cosmic Interval Dynamics — From Statistical Anomaly to Theoretical Framework
  Yoshimitsu Katayama · Zenodo (CERN European Organ... · May 17, 2026

  This paper presents the Ma Resonance Theory v2.0, a theoretical framework resolving the central mechanism objection to Tendo Economics: the absence of a direct causal link between IceCube neutrino detection and gold market returns. The reso…

• When Are Two Networks the Same? Tensor Similarity for Mechanistic Interpretability
  ML Nissen Gonzalez, Melwina Albuquerque, Laurence Wroe, Jacob Meyer Cohen et al. · arXiv · May 14, 2026

  Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either empirical behaviour, leaving them blind to…

• Widening the Gap: Exploiting LLM Quantization via Outlier Injection
  Xiaohua Zhan, Kazuki Egashira, Robin Staab, Mark Vero et al. · arXiv · May 14, 2026

  LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits mal…

• Attractor-Vascular Coupling Theory: Formal Grounding and Empirical Validation for AAMI-Standard Cuffless Blood Pressure Estimation from Smartphone Photoplethysmography
  Timothy Oladunni, Farouk Ganiyu Adewumi · arXiv · May 11, 2026

  This work proposes Attractor-Vascular Coupling Theory (AVCT), a mathematical framework showing that cardiac attractor geometry encodes blood pressure (BP) information sufficient for AAMI-standard estimation, and validates the theory through…

• Normalizing Trajectory Models
  Jiatao Gu, Tianrong Chen, Ying Shen, David Berthelot et al. · arXiv · May 8, 2026

  Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through distillation, con…

• Self-supervised Point Cloud Mining for Surface Anomaly Detection in Additive Manufacturing
  Hao Wang, Yujing Yang, Chen Kan · Journal of Computing and In... · May 8, 2026

  Abstract With rapid advances in 3-dimensional (3D) metrology, point cloud data are increasingly available for surface quality inspection in additive manufacturing (AM). Compared to images, point clouds capture richer geometric information f…

• Taming Outlier Tokens in Diffusion Transformers
  Xiaoyu Wu, Yifei Wang, Tsu-Jui Fu, Liang-Chieh Chen et al. · arXiv · May 6, 2026

  We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number of high-norm tokens that attract disproportionate attention while carrying limite…

• Conditional outlier detection for clinical alerting
  Milos Hauskrecht, Michal Valko, Shyam Visweswaran, Iyad Batal et al. · arXiv · May 6, 2026

  We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management actions using past patient cases stored in an electronic health record (EHR) system. Our hypothesis is that patient-management actions that …

• Conditional outlier detection for clinical alerting
  Miloš Hauskrecht, Michal Vaľko, Iyad Batal, Gilles Clermont et al. · PubMed · May 6, 2026

  We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management actions using past patient cases stored in an electronic health record (EHR) system. Our hypothesis is that patient-management actions that …

• Unsupervised Machine Learning for Detecting Structural Anomalies in European Regional Statistics
  Bogdan Oancea · arXiv · May 4, 2026

  Ensuring the coherence of regional socio-economic statistics is a central task for national statistical institutes. Traditional validation tools, such as range edits, ratio checks, or univariate outlier detection, are effective for identify…