{"total":113,"rows":[{"id":"2403.07366","title":"Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors","created":"2024-03-12","cited_by_count":106,"area":null},{"id":"2306.02050","title":"Provable Dynamic Fusion for Low-Quality Multimodal Data","created":"2023-06-03","cited_by_count":82,"area":null},{"id":"2103.08902","title":"Differentiable Learning Under Triage","created":"2021-03-16","cited_by_count":76,"area":null},{"id":"2203.10192","title":"Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantification","created":"2022-03-18","cited_by_count":73,"area":null},{"id":"2206.06640","title":"Confidence Score for Source-Free Unsupervised Domain Adaptation","created":"2022-06-14","cited_by_count":59,"area":null},{"id":"2106.02395","title":"DOCTOR: A Simple Method for Detecting Misclassification Errors","created":"2021-06-04","cited_by_count":53,"area":null},{"id":"2211.15259","title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","created":"2022-11-28","cited_by_count":52,"area":null},{"id":"2303.02970","title":"Rethinking Confidence Calibration for Failure Prediction","created":"2023-03-06","cited_by_count":43,"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":"2302.11874","title":"What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers","created":"2023-02-23","cited_by_count":35,"area":null},{"id":"2209.08928","title":"UMIX: Improving Importance Weighting for Subpopulation Shift via Uncertainty-Aware Mixup","created":"2022-09-19","cited_by_count":34,"area":null},{"id":"2402.10430","title":"Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models","created":"2024-02-16","cited_by_count":32,"area":null},{"id":"2207.07506","title":"Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data","created":"2022-07-15","cited_by_count":27,"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":"2308.09887","title":"Calibrating Uncertainty for Semi-Supervised Crowd Counting","created":"2023-08-19","cited_by_count":22,"area":null},{"id":"2205.13532","title":"Selective Prediction via Training Dynamics","created":"2022-05-26","cited_by_count":20,"area":null},{"id":"2108.11800","title":"Efficient Out-of-Distribution Detection Using Latent Space of $\\beta$-VAE for Cyber-Physical Systems","created":"2021-08-26","cited_by_count":19,"area":null},{"id":"2110.13741","title":"Disrupting Deep Uncertainty Estimation Without Harming Accuracy","created":"2021-10-26","cited_by_count":19,"area":null},{"id":"2112.00337","title":"A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks","created":"2021-12-01","cited_by_count":19,"area":null},{"id":"2210.12787","title":"Respecting Transfer Gap in Knowledge Distillation","created":"2022-10-23","cited_by_count":18,"area":"distill"},{"id":"2302.04002","title":"The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition","created":"2023-02-08","cited_by_count":16,"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":"2305.15508","title":"How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks","created":"2023-05-24","cited_by_count":16,"area":null},{"id":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"area":null},{"id":"2410.15361","title":"A Novel Characterization of the Population Area Under the Risk Coverage Curve (AURC) and Rates of Finite Sample Estimators","created":"2024-10-20","cited_by_count":15,"area":null},{"id":"2303.01201","title":"Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection","created":"2023-03-02","cited_by_count":14,"area":null},{"id":"2405.05160","title":"Selective Classification Under Distribution Shifts","created":"2024-05-08","cited_by_count":12,"area":null},{"id":"2205.12528","title":"LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification","created":"2022-05-25","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":"2304.06540","title":"Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future","created":"2023-04-13","cited_by_count":10,"area":null},{"id":"2403.02886","title":"Revisiting Confidence Estimation: Towards Reliable Failure Prediction","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2110.06427","title":"Dense Uncertainty Estimation","created":"2021-10-13","cited_by_count":9,"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":"2307.10440","title":"Confidence Estimation Using Unlabeled Data","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2403.00543","title":"SURE: SUrvey REcipes for building reliable and robust deep networks","created":"2024-03-01","cited_by_count":8,"area":null},{"id":"2206.06661","title":"Toward Student-Oriented Teacher Network Training For Knowledge Distillation","created":"2022-06-14","cited_by_count":7,"area":"distill"},{"id":"2304.04906","title":"Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing","created":"2023-04-11","cited_by_count":7,"area":null},{"id":"2405.03730","title":"Tilt your Head: Activating the Hidden Spatial-Invariance of Classifiers","created":"2024-05-06","cited_by_count":7,"area":null},{"id":"2405.11533","title":"Hierarchical Selective Classification","created":"2024-05-19","cited_by_count":7,"area":null},{"id":"2412.07169","title":"Rate-In: Information-Driven Adaptive Dropout Rates for Improved Inference-Time Uncertainty Estimation","created":"2024-12-10","cited_by_count":7,"area":null},{"id":"2603.21172","title":"Entropy Alone is Insufficient for Safe Selective Prediction in LLMs","created":"2026-03-22","cited_by_count":7,"area":null},{"id":"2402.00084","title":"EPSD: Early Pruning with Self-Distillation for Efficient Model Compression","created":"2024-01-31","cited_by_count":6,"area":"distill"},{"id":"2411.01981","title":"Typicalness-Aware Learning for Failure Detection","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2506.16589","title":"Spatially-Aware Evaluation of Segmentation Uncertainty","created":"2025-06-19","cited_by_count":6,"area":null},{"id":"2402.01476","title":"Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2402.08384","title":"Selective Learning: Towards Robust Calibration with Dynamic Regularization","created":"2024-02-13","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":"2308.03179","title":"Empirical Optimal Risk to Quantify Model Trustworthiness for Failure Detection","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2505.18636","title":"Asymmetric Duos: Sidekicks Improve Uncertainty","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2509.16696","title":"Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models","created":"2025-09-20","cited_by_count":3,"area":null},{"id":"2510.09473","title":"D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models","created":"2025-10-10","cited_by_count":3,"area":"mllm"},{"id":"2511.10370","title":"SHRUG-FM: Reliability-Aware Foundation Models for Earth Observation","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2605.12446","title":"ORCE: Order-Aware Alignment of Verbalized Confidence in Large Language Models","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2608.26846","title":"Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2106.09385","title":"On Deep Neural Network Calibration by Regularization and its Impact on Refinement","created":"2021-06-17","cited_by_count":2,"area":null},{"id":"2210.10897","title":"Window-Based Distribution Shift Detection for Deep Neural Networks","created":"2022-10-19","cited_by_count":2,"area":null},{"id":"2302.01440","title":"Generalized Uncertainty of Deep Neural Networks: Taxonomy and Applications","created":"2023-02-02","cited_by_count":2,"area":null},{"id":"2304.04148","title":"Reweighted Mixup for Subpopulation Shift","created":"2023-04-09","cited_by_count":2,"area":null},{"id":"2309.16364","title":"FG-NeRF: Flow-GAN based Probabilistic Neural Radiance Field for Independence-Assumption-Free Uncertainty Estimation","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2410.14975","title":"Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation","created":"2024-10-19","cited_by_count":2,"area":"mllm"},{"id":"2502.13954","title":"Latent Distribution Decoupling: A Probabilistic Framework for Uncertainty-Aware Multimodal Emotion Recognition","created":"2025-02-19","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":"2602.04924","title":"Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2602.11908","title":"When Should LLMs Be Less Specific? Selective Abstraction for Reliable Long-Form Text Generation","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2602.20449","title":"Protein Language Models Diverge from Natural Language: Comparative Analysis and Improved Inference","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2604.27715","title":"Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining","created":"2026-04-30","cited_by_count":2,"area":"mllm"},{"id":"2605.19539","title":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2607.14817","title":"Evaluating Epistemic Uncertainty: Beyond OOD Detection and Active Learning","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2110.10206","title":"Evaluating and Improving Interactions with Hazy Oracles","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2206.02152","title":"Which models are innately best at uncertainty estimation?","created":"2022-06-05","cited_by_count":1,"area":null},{"id":"2402.10665","title":"Soft Dice Confidence: A Near-Optimal Confidence Estimator for Selective Prediction in Semantic Segmentation","created":"2024-02-16","cited_by_count":1,"area":null},{"id":"2402.14184","title":"Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2407.02138","title":"Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Tasks","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2410.20432","title":"Integrating uncertainty quantification into randomized smoothing based robustness guarantees","created":"2024-10-27","cited_by_count":1,"area":null},{"id":"2410.23046","title":"Legitimate ground-truth-free metrics for deep uncertainty classification scoring","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2503.20492","title":"Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Models","created":"2025-03-26","cited_by_count":1,"area":"mllm"},{"id":"2505.22843","title":"On the Reliability and Stability of Selective Methods in Malware Classification Tasks","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2601.22570","title":"Leveraging Data to Say No: Memory Augmented Plug-and-Play Selective Prediction","created":"2026-01-30","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":"2605.22864","title":"Reading Calibrated Uncertainty from Language Model Trajectories","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.07822","title":"The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.13497","title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2609.02057","title":"Monitoring Web Agents Without Internal Signals: Observable Trajectories and Key-Step Supervision","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2106.11119","title":"Graceful Degradation and Related Fields","created":"2021-06-21","cited_by_count":0,"area":null},{"id":"2204.14255","title":"Human-in-the-loop online multi-agent approach to increase trustworthiness in ML models through trust scores and data augmentation","created":"2022-04-29","cited_by_count":0,"area":null},{"id":"2408.16792","title":"Uncertainty-aware segmentation for rainfall prediction post processing","created":"2024-08-28","cited_by_count":0,"area":null},{"id":"2505.11669","title":"OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2505.14124","title":"Intra-class Patch Swap for Self-Distillation","created":"2025-05-20","cited_by_count":0,"area":"distill"},{"id":"2505.23463","title":"Revisiting Reweighted Risk for Calibration: AURC, Focal, and Inverse Focal Loss","created":"2025-05-29","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":"2604.03614","title":"One-Shot Localisation of the Global Minimum of a Noisy One-Dimensional Function: An Iterative Neural Minimizer Compared with Set Transformers and Classical Estimators","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.08454","title":"Less Data Approximates More: Earning Faithful Confidence in High-Stakes Domains","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.12044","title":"VISTA: Validation-Informed Trajectory Adaptation via Self-Distillation","created":"2026-04-13","cited_by_count":0,"area":"distill"},{"id":"2604.12719","title":"Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning","created":"2026-04-14","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":"2606.09390","title":"Real-time body pose non-verbal communication with a consistency-based reliability measure","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.00083","title":"Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust","created":"2026-06-30","cited_by_count":0,"area":"mechinterp"},{"id":"2608.08398","title":"Estimating Uncertainty in Galaxy Morphology Classification","created":"2026-08-09","cited_by_count":0,"area":null}],"next_cursor":"100"}