← Back to all news
arXiv AI By Daisuke Yamada, Harit Vishwakarma, Ramya Korlakai Vinayak

ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection

Read the original on arXiv AI →

arXiv:2505. 02299v2 Announce Type: replace-cross Abstract: Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment---posing serious risks in safety-critical domains.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

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
benchmarkssafety
More like this →
arXiv Machine Learning
Sep 11

Optimizing Three Critical Factors for Practical and Effective OOD Detection Fine-Tuning

The paper introduces a framework for out-of-distribution (OOD) detection that addresses the trade‑off between detection performance and classification accuracy caused by fine‑tuning with auxiliary outlier data. It optimizes three factors—model reminder, data sampling, and representation learning—by proposing Self‑Knowledge Distillation to preserve accuracy, Semi‑hard Outlier Sampling to enhance detection with minimal data, and Outlier‑aware Supervised Contrastive Learning to improve ID‑OOD separability. The combined approach yields cumulative gains, outperforming existing methods on diverse benchmarks, especially in long‑tailed scenarios, and offers a robust baseline for real‑world OOD detection.

By Hyunjun Choi, JaeHo Chung, Hawook Jeong
fine-tuningefficiencybenchmarks
More like this →
arXiv Machine Learning
Jul 22

RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Deployment

arXiv:2602. 01515v2 Announce Type: replace-cross Abstract: Deploying learned control policies is risky because policies that appear robust in simulation can confidently enter out-of-distribution (OOD) states after Sim-to-Real transfer, causing silent failures and potential hardware damage.

By Humphrey Munn, Brendan Tidd, Peter Bohm, Marcus Gallagher, David Howard
llmsrobotics
More like this →