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
arXiv:2606. 10877v1 Announce Type: new Abstract: Occlusion-based attribution methods provide an intuitive way to estimate feature importance by perturbing input features and measuring the resulting change in model output.
By Thodoris Lymperopoulos, Ioannis Kakogeorgiou, Denia Kanellopoulou
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
arXiv:2602. 09689v2 Announce Type: replace Abstract: Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data.
By Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Adam Hazimeh, Pascal Frossard
arXiv:2510. 06505v2 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection plays a crucial role in ensuring the robustness of machine learning systems deployed in real-world applications.
By Momin Abbas, Ali Falahati, Hossein Goli, Mohammad Mohammadi Amiri
arXiv:2610.35457v1 Announce Type: cross
Abstract: Bayesian variants of Low-Rank Adaptation (LoRA) provide principled uncertainty estimation when fine-tuning large foundation models, but require speci...
By Tomasz Ku\'smierczyk, Eliezer de Souza da Silva, Marcin Sendera
The paper investigates whether the performance of anomaly detection systems can be predicted without labeled anomalies. For kNN-based detectors, it derives a lower bound on AUC that links detection performance to the separation and variance of inlier and outlier scores, and uses this to analyze how density variation, intrinsic dimensionality, and domain mismatch affect score variability. The authors introduce pseudo‑anomaly probes that provide a reference for estimating relative score separation, and demonstrate through experiments on DCASE benchmarks that these probes enable anomaly‑free model selection to outperform conventional development‑set selection, especially under domain shift.
By Kevin Wilkinghoff, Zheng-Hua Tan
The paper investigates how spectral statistics, particularly RankMe and covariance effective rank, behave when large language models (LLMs) undergo post‑training in non‑stationary environments. In controlled experiments on Qwen3‑0.6B, data duplication causes a 75% increase in held‑out loss while simultaneously raising both original and centred RankMe, indicating spectral dispersion rather than rank collapse. The authors demonstrate that a two‑sided, multichannel sequential monitor can detect various damage regimes but does not predict held‑out loss earlier and requires healthy calibration data.
By Zhaohui Geoffrey Wang
TaRA: Training-Aware Low-Rank Adaptation Initialization proposes a new way to initialize LoRA by aligning the gradients of low‑rank factors with those of the full‑rank weight matrix. This approach directly incorporates training dynamics, improving gradient fidelity at the start of fine‑tuning while adding negligible computational cost. Experiments on a variety of challenging fine‑tuning tasks show that TaRA consistently outperforms existing state‑of‑the‑art initialization methods, offering a simple, robust, and scalable solution for effective LoRA initialization.
By Taehyeon Kim, Eunhyeok Park
arXiv:2604. 08572v2 Announce Type: replace Abstract: State-of-the-art post-hoc out-of-distribution detection methods rely on intermediate layer activation editing.
By Gianluca Guglielmo, Marc Masana
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.
By Daisuke Yamada, Harit Vishwakarma, Ramya Korlakai Vinayak
arXiv:2606. 16454v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pre-trained models to downstream tasks by parameterizing weight updates with low-rank matrices.
By Junghun Oh, Sungyong Baik, Kyoung Mu Lee