arXiv Machine Learning June 16, 2026 By S. A. K. Leeney, W. J. Handley, H. T. J. Bevins, E. de Lera Acedo

Neural Bayesian Anomaly Mitigation: A Robust Loss that Doubles as an Unsupervised Contamination Classifier

Read the original on arXiv Machine Learning →

arXiv:2606. 16524v1 Announce Type: new Abstract: Engineered robust losses such as Huber, Student-$t$, and generalised cross-entropy make supervised models tolerant of contamination but cannot answer which observations are corrupted.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 30

What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamics

arXiv:2606. 29791v1 Announce Type: cross Abstract: Outlier detection (OD) aims to identify anomalous instances by learning the underlying structure of normal data (inliers), and is particularly challenging in fully unsupervised settings where no information about anomalies is available during training.

By Kunwoong Kim, Dongha Kim

benchmarks

arXiv Machine Learning

Jul 21

AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels

arXiv:2605. 28021v2 Announce Type: replace Abstract: Out-of-distribution (OOD) detection is essential for deploying machine learning models in open-world and safety-critical scenarios, where test inputs may deviate from the training distribution and overconfident predictions on unknown samples can lead to unreliable decisions.

By Fengqiang Wan, Qing-Yuan Jiang, Fu Shen, Yang Yang

benchmarks safety

arXiv Machine Learning

Jun 11

TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data

arXiv:2606. 11844v1 Announce Type: new Abstract: Continual anomaly detection in tabular data is challenging and remains largely underexplored, particularly in settings with heterogeneous feature schemas, distribution shifts, and severe class imbalance.

By Dayananda Herurkar, Federico Raue, Joachim Folz, J\"orn Hees, Andreas Dengel

fine-tuning efficiency

arXiv Machine Learning

Jun 30

ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data

arXiv:2408. 16028v4 Announce Type: replace-cross Abstract: Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data.

By Weizhou Wang, Eric Liu, Xiangyu Guo, Xiao Hu, Ilya Grishchenko, David Lie

llms benchmarks

Hugging Face Trending Papers

Aug 10

ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detection

Industrial anomaly detection (IAD) requires identifying fine-grained deviations from normal visual patterns. Multimodal large language models (MLLMs) can improve recognition accuracy by comparing query images with references at inference time, but these benefits rely on additional retrieval and processing.

llms efficiency multimodal benchmarks

arXiv Machine Learning

Jun 2

CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models

arXiv:2606. 01695v1 Announce Type: new Abstract: Adversaries can implant latent harmful behavior by poisoning as few as 1% of fine-tuning examples.

By Swapnil Parekh

llms fine-tuning safety

Related stories

What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamics

AOE: Exhaustive Out-of-Distribution Detection via Recalibrating Outlier Labels

TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data

ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data

ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detection

CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models