{"total":140,"rows":[{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674,"area":null},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390,"area":null},{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"area":null},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151,"area":null},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2106.09647","title":"Deep Learning Through the Lens of Example Difficulty","created":"2021-06-17","cited_by_count":141,"area":null},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121,"area":null},{"id":"2107.03315","title":"Predicting with Confidence on Unseen Distributions","created":"2021-07-07","cited_by_count":116,"area":null},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104,"area":null},{"id":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2206.06602","title":"Deep Isolation Forest for Anomaly Detection","created":"2022-06-14","cited_by_count":92,"area":null},{"id":"2111.15430","title":"The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration","created":"2021-11-30","cited_by_count":91,"area":null},{"id":"2106.04015","title":"Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning","created":"2021-06-07","cited_by_count":82,"area":null},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81,"area":null},{"id":"2110.14012","title":"Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification","created":"2021-10-26","cited_by_count":80,"area":null},{"id":"2104.03829","title":"Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions","created":"2021-04-08","cited_by_count":68,"area":null},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67,"area":null},{"id":"2110.12899","title":"No One Representation to Rule Them All: Overlapping Features of Training Methods","created":"2021-10-20","cited_by_count":58,"area":null},{"id":"2207.09239","title":"Assaying Out-Of-Distribution Generalization in Transfer Learning","created":"2022-07-19","cited_by_count":53,"area":null},{"id":"2106.14568","title":"Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity","created":"2021-06-28","cited_by_count":44,"area":null},{"id":"2204.04516","title":"Uncertainty-Informed Deep Learning Models Enable High-Confidence Predictions for Digital Histopathology","created":"2022-04-09","cited_by_count":37,"area":null},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2110.13786","title":"Diversity and Generalization in Neural Network Ensembles","created":"2021-10-26","cited_by_count":32,"area":null},{"id":"2110.13511","title":"AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantification","created":"2021-10-26","cited_by_count":31,"area":null},{"id":"2305.09235","title":"Synthetic data, real errors: how (not) to publish and use synthetic data","created":"2023-05-16","cited_by_count":29,"area":null},{"id":"2105.13283","title":"Deep Ensembles from a Bayesian Perspective","created":"2021-05-27","cited_by_count":27,"area":null},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27,"area":null},{"id":"2102.09009","title":"BORE: Bayesian Optimization by Density-Ratio Estimation","created":"2021-02-17","cited_by_count":26,"area":null},{"id":"2206.07647","title":"Hyperparameter Sensitivity in Deep Outlier Detection: Analysis and a Scalable Hyper-Ensemble Solution","created":"2022-06-15","cited_by_count":24,"area":null},{"id":"2103.10919","title":"Robustness via Cross-Domain Ensembles","created":"2021-03-19","cited_by_count":23,"area":null},{"id":"2106.10760","title":"On Stein Variational Neural Network Ensembles","created":"2021-06-20","cited_by_count":21,"area":null},{"id":"2310.11122","title":"Sensitivity-Aware Amortized Bayesian Inference","created":"2023-10-17","cited_by_count":20,"area":null},{"id":"2405.14438","title":"LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks","created":"2024-05-23","cited_by_count":20,"area":null},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"area":null},{"id":"2304.03981","title":"Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification","created":"2023-04-08","cited_by_count":18,"area":null},{"id":"2102.13640","title":"NOMU: Neural Optimization-based Model Uncertainty","created":"2021-02-26","cited_by_count":16,"area":null},{"id":"2105.10827","title":"Orthogonal Ensemble Networks for Biomedical Image Segmentation","created":"2021-05-22","cited_by_count":16,"area":null},{"id":"2111.13280","title":"Efficient Self-Ensemble for Semantic Segmentation","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2207.11727","title":"Can we achieve robustness from data alone?","created":"2022-07-24","cited_by_count":16,"area":null},{"id":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2306.08271","title":"Multiclass Confidence and Localization Calibration for Object Detection","created":"2023-06-14","cited_by_count":16,"area":null},{"id":"2105.06791","title":"Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations","created":"2021-05-14","cited_by_count":15,"area":null},{"id":"2105.04471","title":"Natural Posterior Network: Deep Bayesian Uncertainty for Exponential Family Distributions","created":"2021-05-10","cited_by_count":13,"area":null},{"id":"2112.12218","title":"Maximum Entropy on Erroneous Predictions (MEEP): Improving model calibration for medical image segmentation","created":"2021-12-22","cited_by_count":13,"area":null},{"id":"2202.11782","title":"Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks","created":"2022-02-23","cited_by_count":13,"area":null},{"id":"2110.08220","title":"Combining Diverse Feature Priors","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2312.13772","title":"Large Language Models are Miscalibrated In-Context Learners","created":"2023-12-21","cited_by_count":12,"area":null},{"id":"2203.08295","title":"Self-Distribution Distillation: Efficient Uncertainty Estimation","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2306.14916","title":"Uncertainty Estimation for Molecules: Desiderata and Methods","created":"2023-06-20","cited_by_count":11,"area":null},{"id":"2204.01618","title":"Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecasting","created":"2022-04-04","cited_by_count":10,"area":null},{"id":"2311.04434","title":"A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space","created":"2023-11-08","cited_by_count":10,"area":null},{"id":"2110.06427","title":"Dense Uncertainty Estimation","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2206.00944","title":"Feature Space Particle Inference for Neural Network Ensembles","created":"2022-06-02","cited_by_count":9,"area":null},{"id":"2208.14698","title":"Bayesian Optimization-based Combinatorial Assignment","created":"2022-08-31","cited_by_count":9,"area":null},{"id":"2201.10908","title":"Improving robustness and calibration in ensembles with diversity regularization","created":"2022-01-26","cited_by_count":8,"area":null},{"id":"2304.04824","title":"Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning","created":"2023-04-10","cited_by_count":8,"area":null},{"id":"2402.08383","title":"Uncertainty Quantification for Forward and Inverse Problems of PDEs via Latent Global Evolution","created":"2024-02-13","cited_by_count":8,"area":null},{"id":"2505.22332","title":"Credal Prediction based on Relative Likelihood","created":"2025-05-28","cited_by_count":8,"area":null},{"id":"2111.08313","title":"Towards Comprehensive Monocular Depth Estimation: Multiple Heads Are Better Than One","created":"2021-11-16","cited_by_count":7,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2206.10566","title":"Ensembling over Classifiers: a Bias-Variance Perspective","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2207.00479","title":"Asynchronous Decentralized Bayesian Optimization for Large Scale Hyperparameter Optimization","created":"2022-07-01","cited_by_count":6,"area":null},{"id":"2302.05098","title":"Confidence-based Reliable Learning under Dual Noises","created":"2023-02-10","cited_by_count":6,"area":null},{"id":"2304.04042","title":"Deep Anti-Regularized Ensembles provide reliable out-of-distribution uncertainty quantification","created":"2023-04-08","cited_by_count":6,"area":null},{"id":"2309.07403","title":"Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance","created":"2023-09-14","cited_by_count":6,"area":null},{"id":"2507.08150","title":"CLEAR: Calibrated Learning for Epistemic and Aleatoric Risk","created":"2025-07-10","cited_by_count":6,"area":null},{"id":"2106.04767","title":"Ex uno plures: Splitting One Model into an Ensemble of Subnetworks","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2107.03815","title":"Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs","created":"2021-07-08","cited_by_count":5,"area":null},{"id":"2110.10645","title":"Combining Different V1 Brain Model Variants to Improve Robustness to Image Corruptions in CNNs","created":"2021-10-20","cited_by_count":5,"area":null},{"id":"2206.00794","title":"Sequential Bayesian Neural Subnetwork Ensembles","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2212.08123","title":"Bayesian posterior approximation with stochastic ensembles","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2412.08776","title":"Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: a system safety case study on sodium fast reactor thermal stratification modeling","created":"2024-12-11","cited_by_count":5,"area":null},{"id":"2107.04369","title":"Multi-headed Neural Ensemble Search","created":"2021-07-09","cited_by_count":4,"area":null},{"id":"2208.11727","title":"Hyperparameter Optimization for Unsupervised Outlier Detection","created":"2022-08-24","cited_by_count":4,"area":null},{"id":"2301.04421","title":"Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspective","created":"2023-01-11","cited_by_count":4,"area":null},{"id":"2402.03187","title":"How Good is a Single Basin?","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2105.14275","title":"Greedy Bayesian Posterior Approximation with Deep Ensembles","created":"2021-05-29","cited_by_count":3,"area":null},{"id":"2210.06436","title":"Deep Combinatorial Aggregation","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2301.04414","title":"How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?","created":"2023-01-11","cited_by_count":3,"area":null},{"id":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2408.07201","title":"Quantification of total uncertainty in the physics-informed reconstruction of CVSim-6 physiology","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2505.11738","title":"Automated Real-time Assessment of Intracranial Hemorrhage Detection AI Using an Ensembled Monitoring Model (EMM)","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2109.07045","title":"Uncertainty Quantification in Medical Image Segmentation with Multi-decoder U-Net","created":"2021-09-15","cited_by_count":2,"area":null},{"id":"2209.09641","title":"Calibrating Segmentation Networks with Margin-based Label Smoothing","created":"2022-09-09","cited_by_count":2,"area":null},{"id":"2210.05387","title":"Sequential Ensembling for Semantic Segmentation","created":"2022-10-08","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":"2302.05807","title":"Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play","created":"2023-02-11","cited_by_count":2,"area":null},{"id":"2307.05476","title":"Fisher-Weighted Merge of Contrastive Learning Models in Sequential Recommendation","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2310.11077","title":"United We Stand: Using Epoch-wise Agreement of Ensembles to Combat Overfit","created":"2023-10-17","cited_by_count":2,"area":null},{"id":"2401.13657","title":"Inadequacy of common stochastic neural networks for reliable clinical decision support","created":"2024-01-24","cited_by_count":2,"area":null},{"id":"2409.16797","title":"Scalable Ensemble Diversification for OOD Generalization and Detection","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2505.14803","title":"SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysis","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2511.17760","title":"When Active Learning Fails, Uncalibrated Out of Distribution Uncertainty Quantification Might Be the Problem","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2603.28182","title":"A Closer Look at Cross-Domain Few-Shot Object Detection: Fine-Tuning Matters and Parallel Decoder Helps","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2604.02719","title":"MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2103.15041","title":"Accurate and Reliable Forecasting using Stochastic Differential Equations","created":"2021-03-28","cited_by_count":1,"area":null},{"id":"2110.09712","title":"Balancing Value Underestimation and Overestimation with Realistic Actor-Critic","created":"2021-10-19","cited_by_count":1,"area":null},{"id":"2112.12728","title":"Latent Time Neural Ordinary Differential Equations","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2202.12297","title":"Embedded Ensembles: Infinite Width Limit and Operating Regimes","created":"2022-02-24","cited_by_count":1,"area":null}],"next_cursor":"100"}