{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2001.06782","title":"Gradient Surgery for Multi-Task Learning","created":"2020-01-19","cited_by_count":1256},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"2107.03342","title":"A Survey of Uncertainty in Deep Neural Networks","created":"2021-07-07","cited_by_count":680},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1701.06548","title":"Regularizing Neural Networks by Penalizing Confident Output Distributions","created":"2017-01-23","cited_by_count":464},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"2006.10108","title":"Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness","created":"2020-06-17","cited_by_count":389},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1901.08846","title":"Improving Adversarial Robustness via Promoting Ensemble Diversity","created":"2019-01-25","cited_by_count":213},{"id":"1803.08533","title":"Understanding Measures of Uncertainty for Adversarial Example Detection","created":"2018-03-22","cited_by_count":177},{"id":"2010.06610","title":"Training independent subnetworks for robust prediction","created":"2020-10-13","cited_by_count":177},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1911.12423","title":"AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning","created":"2019-11-27","cited_by_count":160},{"id":"2107.08924","title":"Epistemic Neural Networks","created":"2021-07-19","cited_by_count":120},{"id":"2106.11642","title":"Repulsive Deep Ensembles are Bayesian","created":"2021-06-22","cited_by_count":104},{"id":"2012.08334","title":"Masksembles for Uncertainty Estimation","created":"2020-12-15","cited_by_count":88},{"id":"2010.14689","title":"Bayesian Deep Learning via Subnetwork Inference","created":"2020-10-28","cited_by_count":87},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81},{"id":"2402.19460","title":"Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks","created":"2024-02-29","cited_by_count":78},{"id":"2301.03962","title":"A Unified Theory of Diversity in Ensemble Learning","created":"2023-01-10","cited_by_count":71},{"id":"2202.06985","title":"Deep Ensembles Work, But Are They Necessary?","created":"2022-02-14","cited_by_count":63},{"id":"2210.09184","title":"Packed-Ensembles for Efficient Uncertainty Estimation","created":"2022-10-17","cited_by_count":49},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48},{"id":"2412.20892","title":"Rethinking Aleatoric and Epistemic Uncertainty","created":"2024-12-30","cited_by_count":42},{"id":"2003.04514","title":"Diversity inducing Information Bottleneck in Model Ensembles","created":"2020-03-10","cited_by_count":27},{"id":"2206.00050","title":"FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation","created":"2022-05-31","cited_by_count":24},{"id":"2405.14438","title":"LoRA-Ensemble: Efficient Uncertainty Modelling for Self-Attention Networks","created":"2024-05-23","cited_by_count":20},{"id":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16},{"id":"2312.15297","title":"Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models","created":"2023-12-23","cited_by_count":15},{"id":"1802.04893","title":"Uncertainty Estimation via Stochastic Batch Normalization","created":"2018-02-13","cited_by_count":11},{"id":"2201.10908","title":"Improving robustness and calibration in ensembles with diversity regularization","created":"2022-01-26","cited_by_count":8},{"id":"2206.02435","title":"Tackling covariate shift with node-based Bayesian neural networks","created":"2022-06-06","cited_by_count":8},{"id":"2412.15758","title":"Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensembles","created":"2024-12-20","cited_by_count":8},{"id":"2510.18358","title":"Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers","created":"2025-10-21","cited_by_count":5},{"id":"2511.10282","title":"Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification","created":"2025-11-13","cited_by_count":4},{"id":"2601.16936","title":"Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles","created":"2026-01-23","cited_by_count":4},{"id":"2204.06404","title":"Receding Neuron Importances for Structured Pruning","created":"2022-04-13","cited_by_count":3},{"id":"2512.20420","title":"Simplifying Multi-Task Architectures Through Task-Specific Normalization","created":"2025-12-23","cited_by_count":1}],"next_cursor":null}