{"total":75,"rows":[{"id":"2402.18563","title":"Approaching Human-Level Forecasting with Language Models","created":"2024-02-28","cited_by_count":107,"area":null},{"id":"2503.02623","title":"Rewarding Doubt: A Reinforcement Learning Approach to Calibrated Confidence Expression of Large Language Models","created":"2025-03-04","cited_by_count":52,"area":null},{"id":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2512.21919","title":"SWE-RM: Execution-free Feedback For Software Engineering Agents","created":"2025-12-26","cited_by_count":28,"area":"lr"},{"id":"2310.04752","title":"A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization","created":"2023-10-07","cited_by_count":24,"area":null},{"id":"2505.18893","title":"Reality Check: A New Evaluation Ecosystem Is Necessary to Understand AI's Real World Effects","created":"2025-05-24","cited_by_count":19,"area":null},{"id":"2406.06487","title":"When is Multicalibration Post-Processing Necessary?","created":"2024-06-10","cited_by_count":18,"area":null},{"id":"2406.10215","title":"DevBench: A multimodal developmental benchmark for language learning","created":"2024-06-14","cited_by_count":13,"area":"mllm"},{"id":"2402.04344","title":"Does confidence calibration improve conformal prediction?","created":"2024-02-06","cited_by_count":12,"area":null},{"id":"2411.02988","title":"Confidence Calibration of Classifiers with Many Classes","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2404.11350","title":"Calibrating Bayesian Learning via Regularization, Confidence Minimization, and Selective Inference","created":"2024-04-17","cited_by_count":7,"area":null},{"id":"2507.19144","title":"Solar Photovoltaic Assessment with Large Language Model","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2410.20199","title":"Rethinking the Uncertainty: A Critical Review and Analysis in the Era of Large Language Models","created":"2024-10-26","cited_by_count":6,"area":"lr"},{"id":"2502.07847","title":"Confidence-calibrated covariate shift correction for few-shot classification in Vision-Language Models","created":"2025-02-11","cited_by_count":6,"area":"mllm"},{"id":"2409.04874","title":"Improving the Finite Sample Estimation of Average Treatment Effects using Double/Debiased Machine Learning with Propensity Score Calibration","created":"2024-09-07","cited_by_count":5,"area":null},{"id":"2408.11598","title":"Improving Calibration by Relating Focal Loss, Temperature Scaling, and Properness","created":"2024-08-21","cited_by_count":4,"area":null},{"id":"2412.19325","title":"Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones","created":"2024-12-26","cited_by_count":4,"area":"inference"},{"id":"2604.21260","title":"Calibeating Prediction-Powered Inference","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2505.01766","title":"Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2511.10439","title":"Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration","created":"2025-11-13","cited_by_count":3,"area":null},{"id":"2407.14185","title":"Achieving Well-Informed Decision-Making in Drug Discovery: A Comprehensive Calibration Study using Neural Network-Based Structure-Activity Models","created":"2024-07-19","cited_by_count":2,"area":null},{"id":"2501.14048","title":"SIDDA: SInkhorn Dynamic Domain Adaptation for Image Classification with Equivariant Neural Networks","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2501.17595","title":"Technical report on label-informed logit redistribution for better domain generalization in low-shot classification with foundation models","created":"2025-01-29","cited_by_count":2,"area":null},{"id":"2502.00305","title":"DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning","created":"2025-02-01","cited_by_count":2,"area":null},{"id":"2503.07958","title":"Pre-trained Models Succeed in Medical Imaging with Representation Similarity Degradation","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2505.23866","title":"Towards Understanding The Calibration Benefits of Sharpness-Aware Minimization","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2507.09768","title":"Knowing When to Quit: Probabilistic Early Exits for Speech Separation","created":"2025-07-13","cited_by_count":2,"area":"inference"},{"id":"2510.26566","title":"Multiclass Local Calibration with the Jensen-Shannon Distance","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2601.16414","title":"PyHealth 2.0: A Comprehensive Open-Source Toolkit for Accessible and Reproducible Clinical Deep Learning","created":"2026-01-23","cited_by_count":2,"area":null},{"id":"2601.21003","title":"Bayesian-LoRA: Probabilistic Low-Rank Adaptation of Large Language Models","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2601.21624","title":"Training Memory in Deep Neural Networks: Mechanisms, Evidence, and Measurement Gaps","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2603.22634","title":"Learning to Trust: How Humans Mentally Recalibrate AI Confidence Signals","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2606.02671","title":"Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2401.08058","title":"Toward Clinically Trustworthy Deep Learning: Applying Conformal Prediction to Intracranial Hemorrhage Detection","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2402.00899","title":"Weakly Supervised Learners for Correction of AI Errors with Provable Performance Guarantees","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2405.06487","title":"Improving Deep Learning Model Calibration for Cardiac Applications using Deterministic Uncertainty Networks and Uncertainty-aware Training","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2410.23272","title":"A Monte Carlo Framework for Calibrated Uncertainty Estimation in Sequence Prediction","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2411.11935","title":"Calibrated and Efficient Sampling-Free Confidence Estimation for LiDAR Scene Semantic Segmentation","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2507.09222","title":"Calibrated and Robust Foundation Models for Vision-Language and Medical Image Tasks Under Distribution Shift","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2507.21670","title":"Probabilistic Consistency in Machine Learning and Its Connection to Uncertainty Quantification","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2508.09346","title":"How Safe Will I Be Given What I Saw? Calibrated Prediction of Safety Chances for Image-Controlled Autonomy","created":"2025-08-12","cited_by_count":1,"area":"wm"},{"id":"2511.00301","title":"A systematic evaluation of uncertainty quantification techniques in deep learning: a case study in photoplethysmography signal analysis","created":"2025-10-31","cited_by_count":1,"area":null},{"id":"2603.19278","title":"HypeLoRA: Hyper-Network-Generated LoRA Adapters for Calibrated Language Model Fine-Tuning","created":"2026-03-01","cited_by_count":1,"area":null},{"id":"2605.21060","title":"Divide et Calibra: Multiclass Local Calibration via Vector Quantization","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.22179","title":"The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions","created":"2026-06-20","cited_by_count":1,"area":null},{"id":"2311.06454","title":"A Saliency-based Clustering Framework for Identifying Aberrant Predictions","created":"2023-11-11","cited_by_count":0,"area":null},{"id":"2401.17042","title":"Forecasting VIX using Bayesian Deep Learning","created":"2024-01-30","cited_by_count":0,"area":null},{"id":"2409.15565","title":"Critic Loss for Image Classification","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2501.02616","title":"Multi-layer Radial Basis Function Networks for Out-of-distribution Detection","created":"2025-01-05","cited_by_count":0,"area":null},{"id":"2503.02119","title":"An Efficient Plugin Method for Metric Optimization of Black-Box Models","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2504.06358","title":"Towards Calibration Enhanced Network by Inverse Adversarial Attack","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2505.08845","title":"Validation of Conformal Prediction in Cervical Atypia Classification","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2506.08066","title":"WWAggr: A Window Wasserstein-based Aggregation for Ensemble Change Point Detection","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.19630","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.16930","title":"Auditability and the Landscape of Distance to Multicalibration","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2511.06433","title":"Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2511.09702","title":"Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2512.04305","title":"How (Mis)calibrated is your Federated CLIP and what to do about it?","created":"2025-12-03","cited_by_count":0,"area":"mllm"},{"id":"2512.10170","title":"Semantic-Aware Confidence Calibration for Automated Audio Captioning","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.13412","title":"Using deep learning for predicting cleansing quality of colon capsule endoscopy images","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.23007","title":"Leveraging Multi-Rater Annotations to Calibrate Object Detectors in Microscopy Imaging","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.15438","title":"Logit Distance Bounds Representational Similarity","created":"2026-02-17","cited_by_count":0,"area":"distill"},{"id":"2602.19024","title":"Towards Calibrating Prompt Tuning of Vision-Language Models","created":"2026-02-22","cited_by_count":0,"area":"mllm"},{"id":"2603.29492","title":"Calibrated Confidence Expression for Radiology Report Generation","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2604.08639","title":"VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.13595","title":"Inducing Artificial Uncertainty in Language Models","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.21652","title":"Look-Closer-Then-Diagnose: Confidence-Aware Ultrasound VQA via Active Zooming","created":"2026-05-20","cited_by_count":0,"area":"mllm"},{"id":"2605.30447","title":"Calibrated Preference Learning: The Case of Label Ranking","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.07170","title":"PUF: Plug-and-Play Uncertainty-Aware Fusion for Online 3D Scene Graph Generation","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.11140","title":"Goodness-of-Fit Tests and Calibration Machine-Learning Algorithms for Logistic Regression with Sparse Data","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.00103","title":"Good Memory Has ECC: Evaluating the Memory of Vision-Language Models Beyond Accuracy","created":"2026-08-31","cited_by_count":0,"area":"mllm"},{"id":"2609.07395","title":"Uncertainty Quantification for LLM Agents: A Taxonomy, an Evaluation Protocol, and an Empirical Study","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.08244","title":"CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion","created":"2026-09-08","cited_by_count":0,"area":"alignment"},{"id":"2609.17386","title":"Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.13693","title":"Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}