{"total":52,"rows":[{"id":"2305.08455","title":"Document Understanding Dataset and Evaluation (DUDE)","created":"2023-05-15","cited_by_count":135,"area":null},{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38,"area":null},{"id":"2407.01032","title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","created":"2024-07-01","cited_by_count":37,"area":null},{"id":"2301.10625","title":"Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment","created":"2023-01-25","cited_by_count":26,"area":null},{"id":"2409.11884","title":"Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances","created":"2024-09-18","cited_by_count":26,"area":null},{"id":"2401.08501","title":"ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation","created":"2024-01-16","cited_by_count":25,"area":null},{"id":"2310.01755","title":"ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms","created":"2023-10-03","cited_by_count":22,"area":null},{"id":"2408.01287","title":"Deep Learning based Visually Rich Document Content Understanding: A Survey","created":"2024-08-02","cited_by_count":21,"area":null},{"id":"2303.08010","title":"Window-Based Early-Exit Cascades for Uncertainty Estimation: When Deep Ensembles are More Efficient than Single Models","created":"2023-03-14","cited_by_count":16,"area":"inference"},{"id":"2301.01054","title":"Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise","created":"2023-01-03","cited_by_count":15,"area":null},{"id":"2409.04796","title":"Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detection","created":"2024-09-07","cited_by_count":15,"area":null},{"id":"2404.01775","title":"A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?","created":"2024-04-02","cited_by_count":13,"area":null},{"id":"2406.03323","title":"Comparative Benchmarking of Failure Detection Methods in Medical Image Segmentation: Unveiling the Role of Confidence Aggregation","created":"2024-06-05","cited_by_count":12,"area":null},{"id":"2305.01481","title":"Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement","created":"2023-05-02","cited_by_count":11,"area":null},{"id":"2403.14715","title":"Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2308.12896","title":"Beyond Document Page Classification: Design, Datasets, and Challenges","created":"2023-08-24","cited_by_count":10,"area":null},{"id":"2311.13355","title":"Unified Classification and Rejection: A One-versus-All Framework","created":"2023-11-22","cited_by_count":9,"area":null},{"id":"2306.04974","title":"Conservative Prediction via Data-Driven Confidence Minimization","created":"2023-06-08","cited_by_count":8,"area":null},{"id":"2407.13708","title":"Are We Ready for Out-of-Distribution Detection in Digital Pathology?","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2502.05275","title":"Interpretable Failure Detection with Human-Level Concepts","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2602.08470","title":"Learning Credal Ensembles via Distributionally Robust Optimization","created":"2026-02-09","cited_by_count":7,"area":null},{"id":"2411.01981","title":"Typicalness-Aware Learning for Failure Detection","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2506.18162","title":"Pitfalls of Conformal Predictions for Medical Image Classification","created":"2025-06-22","cited_by_count":6,"area":null},{"id":"2307.14729","title":"Understanding Silent Failures in Medical Image Classification","created":"2023-07-27","cited_by_count":5,"area":null},{"id":"2309.00688","title":"Jointly Exploring Client Drift and Catastrophic Forgetting in Dynamic Learning","created":"2023-09-01","cited_by_count":5,"area":null},{"id":"2603.16728","title":"The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language Models","created":"2026-03-17","cited_by_count":5,"area":"lr"},{"id":"2404.12599","title":"QUTE: Quantifying Uncertainty in TinyML with Early-exit-assisted ensembles for model-monitoring","created":"2024-04-19","cited_by_count":4,"area":"inference"},{"id":"2410.01690","title":"Why context matters in VQA and Reasoning: Semantic interventions for VLM input modalities","created":"2024-10-02","cited_by_count":4,"area":"lr"},{"id":"2405.18686","title":"Rejection via Learning Density Ratios","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2406.10775","title":"A Rate-Distortion View of Uncertainty Quantification","created":"2024-06-16","cited_by_count":3,"area":null},{"id":"2505.23745","title":"To Trust Or Not To Trust Your Vision-Language Model's Prediction","created":"2025-05-29","cited_by_count":3,"area":"mllm"},{"id":"2408.17337","title":"Evaluating Reliability in Medical DNNs: A Critical Analysis of Feature and Confidence-Based OOD Detection","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2510.20242","title":"What Does It Take to Build a Performant Selective Classifier?","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2602.18094","title":"OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models","created":"2026-02-20","cited_by_count":2,"area":"mllm"},{"id":"2312.06077","title":"An Ambiguity Measure for Recognizing the Unknowns in Deep Learning","created":"2023-12-11","cited_by_count":1,"area":null},{"id":"2406.08226","title":"DistilDoc: Knowledge Distillation for Visually-Rich Document Applications","created":"2024-06-12","cited_by_count":1,"area":"distill"},{"id":"2602.22747","title":"Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Study","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.02200","title":"Adaptive Confidence Regularization for Multimodal Failure Detection","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.29941","title":"Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2411.15060","title":"Hallucination Detection in Virtually-Stained Histology: A Latent Space Baseline","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2504.14545","title":"TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Data","created":"2025-04-20","cited_by_count":0,"area":null},{"id":"2507.22576","title":"COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2511.11934","title":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2603.03903","title":"From Misclassifications to Outliers: Joint Reliability Assessment in Classification","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.15421","title":"U-SEG: Uncertainty in SEGmentation -- A systematic multi-variable exploration","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.20490","title":"ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.00928","title":"Subtype Robustness Is Not Just Accuracy: Calibration Under Unseen Subtype Shift","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.06571","title":"Vision-Language Model Confidence Is Not a Property of the Answer","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.04276","title":"FailSAE: Towards Interpretable Failure Prediction for Vision-Language Models via Sparse Autoencoders","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.30714","title":"CRC-Router: Risk-Constrained Routing for Medical Agentic AI Systems","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.39429","title":"Towards Trustworthy AI for Glioma Diagnosis: A Task-Aware Evaluation of Uncertainty Quantification","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.19378","title":"Robust Explanatory Analysis for Structured Optimization Networks (REASON) in Learning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}