{"total":15,"items":[{"citing_arxiv_id":"2605.31155","ref_index":45,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection","primary_cat":"cs.LG","submitted_at":"2026-05-29T11:04:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Hyperspherical time-frequency representations learned via von Mises-Fisher likelihood improve OOD detection on UCR and UEA archives using k-NN and Mahalanobis scores over contrastive baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17373","ref_index":64,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","primary_cat":"cs.LG","submitted_at":"2026-05-17T10:30:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FML-Bench shows a simple greedy hill-climber nearly matches tree search on dense-opportunity tasks while an adaptive agent that broadens search on stagnation outperforms six baselines across 18 tasks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.07821","ref_index":70,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis","primary_cat":"cs.CV","submitted_at":"2026-05-08T14:51:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"OCO uses object co-occurrence analysis to divide OOD detection into scenarios based on ID training data patterns for improved near-OOD performance.","context_count":1,"top_context_role":"dataset","top_context_polarity":"use_dataset","context_text":"Openslot: Mixed open-set recognition with object-centric learning.arXiv preprint arXiv:2407.02386, 2024. 8 [69] Jinsong Zhang, Qiang Fu, Xu Chen, Lun Du, Zelin Li, Gang Wang, Xiaoguang Liu, Shi Han, and Dongmei Zhang. Out- of-distribution detection based on in-distribution data pat- terns memorization with modern hopfield energy. InICLR, 2023. 1, 5, 6, 7, 8 [70] Jingyang Zhang, Jingkang Yang, Pengyun Wang, Haoqi Wang, Yueqian Lin, Haoran Zhang, Yiyou Sun, Xue- feng Du, Kaiyang Zhou, Wayne Zhang, Yixuan Li, Ziwei Liu, Yiran Chen, and Hai Li. Openood v1.5: Enhanced benchmark for out-of-distribution detection.arXiv preprint arXiv:2306.09301, 2023. 5 [71] Tianren Zhang, Chujie Zhao, Guanyu Chen, Yizhou Jiang,"},{"citing_arxiv_id":"2605.05964","ref_index":10,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Uncertainty Estimation via Hyperspherical Confidence Mapping","primary_cat":"cs.LG","submitted_at":"2026-05-07T10:11:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"HCM estimates uncertainty in neural network outputs by quantifying violation of a unit hypersphere constraint on the normalized direction vector.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08191","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Robust Out-of-Distribution Detection Framework via Synergistic Smoothing","primary_cat":"cs.CV","submitted_at":"2026-05-05T15:45:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ROSS combines median smoothing with local instability measurement to create a robust OOD detector that outperforms prior methods by up to 40 AUROC points on CIFAR and ImageNet benchmarks while defending symmetrically against score attacks.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"We then assess the robustness of ROSS under adversarial conditions by benchmarking it against established OOD de- tection methods subjected to gradient-based attacks. 5.1. Experimental Setup Datasets.We evaluate our method using three ID datasets: CIFAR-10, CIFAR-100 [18] and ImageNet [10]. To ensure comparability with existing benchmarks, we adopt the stan- dardised evaluation protocol from OpenOOD [36]. OOD datasets are categorised as either near-OOD, which are se- mantically different but visually similar to the ID data, or far-OOD, which differ both visually and semantically and lie further from the ID distribution. For CIFAR-10, near-OOD datasets are CIFAR-100 and TinyImageNet (TIN) [19], and far-OOD datasets are MNIST [20], SVHN [29], Texture [8], and Places365 [37]."},{"citing_arxiv_id":"2604.26409","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Sparsity as a Key: Unlocking New Insights from Latent Structures for Out-of-Distribution Detection","primary_cat":"cs.CV","submitted_at":"2026-04-29T08:23:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Sparse autoencoders on ViT class tokens reveal stable Class Activation Profiles for in-distribution data, enabling OOD detection via divergence from core energy profiles.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.10672","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"One-Step Score-Based Density Ratio Estimation","primary_cat":"stat.ML","submitted_at":"2026-04-12T14:53:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OS-DRE performs score-based density ratio estimation in one step by approximating the temporal score component with a closed-form RBF frame and providing error bounds from approximation theory.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08639","ref_index":23,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning","primary_cat":"cs.LG","submitted_at":"2026-04-09T17:22:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"VOLTA, consisting of a deep encoder with learnable prototypes plus cross-entropy and post-hoc temperature scaling, matches or exceeds ten UQ baselines in accuracy, achieves lower expected calibration error, and performs well on out-of-distribution detection across CIFAR, SVHN, and corruption shifts.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.02618","ref_index":73,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs","primary_cat":"cs.CV","submitted_at":"2026-03-03T05:44:47+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"InterNeg improves OOD detection in VLMs by using inter-modal distance criteria for negative text selection and by inverting high-confidence OOD images into additional negative text embeddings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.02409","ref_index":73,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Catalyst: Out-of-Distribution Detection via Elastic Scaling","primary_cat":"cs.CV","submitted_at":"2026-02-02T18:08:33+00:00","verdict":"CONDITIONAL","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Catalyst improves OOD detection by multiplicatively scaling baseline scores using channel-wise statistics from pre-pooling feature maps, reducing average FPR by 22-33% on standard benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.15065","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background","primary_cat":"cs.CV","submitted_at":"2026-01-21T15:12:11+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A new framework adds adaptive background patch suppression via entropy weighting and confusable foreground patch rectification to existing FG-BG methods, significantly improving few-shot OOD detection.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.19996","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RankOOD -- Class Ranking-based Out-of-Distribution Detection","primary_cat":"cs.LG","submitted_at":"2025-11-25T07:02:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RankOOD detects out-of-distribution samples by training a model to predict fixed class-specific ranking permutations via the Plackett-Luce loss, achieving a 4.3% FPR95 reduction on near-OOD TinyImageNet.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2511.11934","ref_index":14,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","primary_cat":"cs.LG","submitted_at":"2025-11-14T23:18:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Benchmark across architectures and shift regimes finds OOD detector rankings shift with representation collapse; proposes NC-based shortlist predictor and PCA filter without extra OOD data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.13576","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Cross-Distribution Diffusion Priors-Driven Iterative Reconstruction for Sparse-View CT","primary_cat":"eess.IV","submitted_at":"2025-09-16T22:35:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CDPIR integrates cross-distribution diffusion priors from a Scalable Interpolant Transformer trained with classifier-free guidance into model-based iterative reconstruction to improve sparse-view CT under out-of-distribution conditions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2502.11638","ref_index":25,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Safeguarding AI in Medical Imaging: Post-Hoc Out-of-Distribution Detection with Normalizing Flows","primary_cat":"cs.CV","submitted_at":"2025-02-17T10:31:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Post-hoc normalizing flows for OOD detection in medical imaging achieve 84.61% AUROC on MedOOD and 93.8% on MedMNIST, outperforming ViM, MDS, and ReAct.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}