{"total":158,"rows":[{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680,"area":null},{"id":"2102.11582","title":"Deep Deterministic Uncertainty: A Simple Baseline","created":"2021-02-23","cited_by_count":200,"area":null},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190,"area":"distill"},{"id":"2204.11423","title":"Trusted Multi-View Classification with Dynamic Evidential Fusion","created":"2022-04-25","cited_by_count":168,"area":null},{"id":"2209.03302","title":"Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?","created":"2022-09-07","cited_by_count":125,"area":null},{"id":"2102.08501","title":"DEUP: Direct Epistemic Uncertainty Prediction","created":"2021-02-16","cited_by_count":104,"area":null},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104,"area":null},{"id":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"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":"2310.19444","title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","created":"2023-10-30","cited_by_count":78,"area":"distill"},{"id":"2308.01222","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","created":"2023-08-02","cited_by_count":75,"area":null},{"id":"2110.03051","title":"Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation","created":"2021-10-06","cited_by_count":71,"area":null},{"id":"2203.06102","title":"Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisation","created":"2022-03-11","cited_by_count":66,"area":null},{"id":"2103.01133","title":"Posterior Meta-Replay for Continual Learning","created":"2021-03-01","cited_by_count":45,"area":null},{"id":"2305.13803","title":"NORM: Knowledge Distillation via N-to-One Representation Matching","created":"2023-05-23","cited_by_count":44,"area":"distill"},{"id":"2103.16367","title":"Complementary Relation Contrastive Distillation","created":"2021-03-29","cited_by_count":42,"area":"distill"},{"id":"2412.14959","title":"Understanding the Dark Side of LLMs' Intrinsic Self-Correction","created":"2024-12-19","cited_by_count":42,"area":"lr"},{"id":"2102.07856","title":"Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification","created":"2021-02-15","cited_by_count":39,"area":null},{"id":"2301.12736","title":"On Second-Order Scoring Rules for Epistemic Uncertainty Quantification","created":"2023-01-30","cited_by_count":38,"area":null},{"id":"2202.03101","title":"Nonparametric Uncertainty Quantification for Single Deterministic Neural Network","created":"2022-02-07","cited_by_count":36,"area":null},{"id":"2207.11347","title":"An Impartial Take to the CNN vs Transformer Robustness Contest","created":"2022-07-22","cited_by_count":34,"area":null},{"id":"2110.14149","title":"Diversity Matters When Learning From Ensembles","created":"2021-10-27","cited_by_count":27,"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":"2202.11091","title":"Efficient and Differentiable Conformal Prediction with General Function Classes","created":"2022-02-22","cited_by_count":26,"area":null},{"id":"2212.12053","title":"On Calibrating Semantic Segmentation Models: Analyses and An Algorithm","created":"2022-12-22","cited_by_count":25,"area":null},{"id":"2409.04720","title":"A Comprehensive Survey on Evidential Deep Learning and Its Applications","created":"2024-09-07","cited_by_count":25,"area":null},{"id":"2102.10809","title":"Local Calibration: Metrics and Recalibration","created":"2021-02-22","cited_by_count":24,"area":null},{"id":"2206.15407","title":"Shifts 2.0: Extending The Dataset of Real Distributional Shifts","created":"2022-06-30","cited_by_count":24,"area":null},{"id":"2103.14473","title":"Distilling a Powerful Student Model via Online Knowledge Distillation","created":"2021-03-26","cited_by_count":22,"area":"distill"},{"id":"2409.08754","title":"Uncertainty Estimation by Density Aware Evidential Deep Learning","created":"2024-09-13","cited_by_count":22,"area":null},{"id":"2106.10760","title":"On Stein Variational Neural Network Ensembles","created":"2021-06-20","cited_by_count":21,"area":null},{"id":"2108.04228","title":"Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition","created":"2021-07-21","cited_by_count":21,"area":null},{"id":"2405.03425","title":"Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models","created":"2024-05-06","cited_by_count":20,"area":null},{"id":"2105.06987","title":"Scaling Ensemble Distribution Distillation to Many Classes with Proxy Targets","created":"2021-05-14","cited_by_count":19,"area":null},{"id":"2307.05772","title":"Random-Set Neural Networks (RS-NN)","created":"2023-07-11","cited_by_count":19,"area":null},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2202.03295","title":"Theoretical characterization of uncertainty in high-dimensional linear classification","created":"2022-02-07","cited_by_count":18,"area":null},{"id":"2208.05642","title":"Self-Knowledge Distillation via Dropout","created":"2022-08-11","cited_by_count":18,"area":"distill"},{"id":"2303.10139","title":"Distill n' Explain: explaining graph neural networks using simple surrogates","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2312.09597","title":"Deep Generative Models for Detector Signature Simulation: A Taxonomic Review","created":"2023-12-15","cited_by_count":18,"area":null},{"id":"2402.06160","title":"Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?","created":"2024-02-09","cited_by_count":18,"area":null},{"id":"2207.10130","title":"Latent Discriminant deterministic Uncertainty","created":"2022-07-20","cited_by_count":17,"area":null},{"id":"2102.12959","title":"Bayesian OOD detection with aleatoric uncertainty and outlier exposure","created":"2021-02-24","cited_by_count":16,"area":null},{"id":"2102.13640","title":"NOMU: Neural Optimization-based Model Uncertainty","created":"2021-02-26","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":"2303.11298","title":"Reliability in Semantic Segmentation: Are We on the Right Track?","created":"2023-03-20","cited_by_count":16,"area":null},{"id":"2303.09843","title":"DUDES: Deep Uncertainty Distillation using Ensembles for Semantic Segmentation","created":"2023-03-17","cited_by_count":15,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2207.07517","title":"On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection","created":"2022-07-15","cited_by_count":14,"area":null},{"id":"2410.11236","title":"Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modeling","created":"2024-10-15","cited_by_count":14,"area":"alignment"},{"id":"2507.01831","title":"Out-of-Distribution Detection Methods Answer the Wrong Questions","created":"2025-07-02","cited_by_count":14,"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":"2304.09426","title":"Decoupled Training for Long-Tailed Classification With Stochastic Representations","created":"2023-04-19","cited_by_count":13,"area":null},{"id":"2401.01484","title":"Uncertainty Regularized Evidential Regression","created":"2024-01-03","cited_by_count":13,"area":null},{"id":"2405.15047","title":"Credal Wrapper of Model Averaging for Uncertainty Estimation in Classification","created":"2024-05-23","cited_by_count":13,"area":null},{"id":"2411.07483","title":"Quantifying Knowledge Distillation Using Partial Information Decomposition","created":"2024-11-12","cited_by_count":13,"area":"distill"},{"id":"2302.06495","title":"Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2104.14203","title":"Rethinking Ensemble-Distillation for Semantic Segmentation Based Unsupervised Domain Adaptation","created":"2021-04-29","cited_by_count":11,"area":null},{"id":"2203.08295","title":"Self-Distribution Distillation: Efficient Uncertainty Estimation","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2301.12378","title":"Towards Inference Efficient Deep Ensemble Learning","created":"2023-01-29","cited_by_count":11,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2305.15781","title":"VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale","created":"2023-05-25","cited_by_count":11,"area":"distill"},{"id":"2106.05515","title":"Understanding the Under-Coverage Bias in Uncertainty Estimation","created":"2021-06-10","cited_by_count":10,"area":null},{"id":"2401.10973","title":"T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration","created":"2024-01-19","cited_by_count":10,"area":null},{"id":"2404.10124","title":"Epistemic Uncertainty Quantification For Pre-trained Neural Network","created":"2024-04-15","cited_by_count":10,"area":null},{"id":"2510.18322","title":"Uncertainty Estimation by Flexible Evidential Deep Learning","created":"2025-10-21","cited_by_count":10,"area":null},{"id":"2103.00869","title":"Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning","created":"2021-03-01","cited_by_count":9,"area":null},{"id":"2110.06427","title":"Dense Uncertainty Estimation","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2204.06546","title":"Disentangling Uncertainty in Machine Translation Evaluation","created":"2022-04-13","cited_by_count":9,"area":null},{"id":"2408.00619","title":"Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection","created":"2024-08-01","cited_by_count":9,"area":null},{"id":"2105.13688","title":"Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving","created":"2021-05-28","cited_by_count":8,"area":null},{"id":"2109.04349","title":"Uncertainty Measures in Neural Belief Tracking and the Effects on Dialogue Policy Performance","created":"2021-09-09","cited_by_count":8,"area":null},{"id":"2110.02609","title":"Deep Classifiers with Label Noise Modeling and Distance Awareness","created":"2021-10-06","cited_by_count":8,"area":null},{"id":"2203.15485","title":"Learning Structured Gaussians to Approximate Deep Ensembles","created":"2022-03-29","cited_by_count":8,"area":null},{"id":"2403.16260","title":"Out-of-Distribution Detection via Deep Multi-Comprehension Ensemble","created":"2024-03-24","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":"2409.12111","title":"Applications of Knowledge Distillation in Remote Sensing: A Survey","created":"2024-09-18","cited_by_count":8,"area":"distill"},{"id":"2505.04950","title":"Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2205.06265","title":"ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training","created":"2022-05-12","cited_by_count":7,"area":null},{"id":"2211.16466","title":"Birds of a Feather Trust Together: Knowing When to Trust a Classifier via Adaptive Neighborhood Aggregation","created":"2022-11-29","cited_by_count":7,"area":null},{"id":"2401.04305","title":"Advancing Deep Active Learning & Data Subset Selection: Unifying Principles with Information-Theory Intuitions","created":"2024-01-09","cited_by_count":7,"area":null},{"id":"2205.01982","title":"Lifelong Ensemble Learning based on Multiple Representations for Few-Shot Object Recognition","created":"2022-05-04","cited_by_count":6,"area":null},{"id":"2206.15047","title":"Improving Ensemble Distillation With Weight Averaging and Diversifying Perturbation","created":"2022-06-30","cited_by_count":6,"area":"distill"},{"id":"2308.16561","title":"MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis","created":"2023-08-31","cited_by_count":6,"area":"distill"},{"id":"2404.03843","title":"Scaling Motion Forecasting Models with Ensemble Distillation","created":"2024-04-05","cited_by_count":6,"area":null},{"id":"2409.18026","title":"ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning","created":"2024-09-26","cited_by_count":6,"area":null},{"id":"2305.10384","title":"Logit-Based Ensemble Distribution Distillation for Robust Autoregressive Sequence Uncertainties","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2403.07282","title":"Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling","created":"2024-03-12","cited_by_count":5,"area":null},{"id":"2410.01628","title":"Stochasticity in Motion: An Information-Theoretic Approach to Trajectory Prediction","created":"2024-10-02","cited_by_count":5,"area":null},{"id":"2505.02277","title":"Epistemic Wrapping for Uncertainty Quantification","created":"2025-05-04","cited_by_count":5,"area":null},{"id":"2201.05938","title":"GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting","created":"2022-01-16","cited_by_count":4,"area":null},{"id":"2206.05608","title":"Gradient Boosting Performs Gaussian Process Inference","created":"2022-06-11","cited_by_count":4,"area":null},{"id":"2208.12464","title":"Dense Depth Distillation with Out-of-Distribution Simulated Images","created":"2022-08-26","cited_by_count":4,"area":"distill"},{"id":"2402.09264","title":"UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers","created":"2024-02-14","cited_by_count":4,"area":null},{"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":"2405.09536","title":"Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised Learning","created":"2024-05-15","cited_by_count":4,"area":null},{"id":"2405.17494","title":"Transitional Uncertainty with Layered Intermediate Predictions","created":"2024-05-25","cited_by_count":4,"area":null}],"next_cursor":"100"}