{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"1906.03671","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","created":"2019-06-09","cited_by_count":610},{"id":"1511.02222","title":"Deep Kernel Learning","created":"2015-11-06","cited_by_count":445},{"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":"2002.09437","title":"Calibrating Deep Neural Networks using Focal Loss","created":"2020-02-21","cited_by_count":357},{"id":"1807.07356","title":"Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks","created":"2018-07-19","cited_by_count":280},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"1906.01620","title":"Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision","created":"2019-06-04","cited_by_count":182},{"id":"1811.12709","title":"Evaluating Bayesian Deep Learning Methods for Semantic Segmentation","created":"2018-11-30","cited_by_count":143},{"id":"2012.06575","title":"Entropy Maximization and Meta Classification for Out-Of-Distribution Detection in Semantic Segmentation","created":"2020-12-09","cited_by_count":133},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121},{"id":"2007.01458","title":"Confidence-Aware Learning for Deep Neural Networks","created":"2020-07-03","cited_by_count":113},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102},{"id":"1611.00336","title":"Stochastic Variational Deep Kernel Learning","created":"2016-11-01","cited_by_count":93},{"id":"2302.13425","title":"A Survey on Uncertainty Quantification Methods for Deep Learning","created":"2023-02-26","cited_by_count":81},{"id":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62},{"id":"2011.12829","title":"All You Need is a Good Functional Prior for Bayesian Deep Learning","created":"2020-11-25","cited_by_count":61},{"id":"1812.03973","title":"Bayesian Layers: A Module for Neural Network Uncertainty","created":"2018-12-10","cited_by_count":57},{"id":"2211.12717","title":"Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks","created":"2022-11-23","cited_by_count":49},{"id":"1707.02476","title":"Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks","created":"2017-07-08","cited_by_count":48},{"id":"2312.17199","title":"Tractable Function-Space Variational Inference in Bayesian Neural Networks","created":"2023-12-28","cited_by_count":41},{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38},{"id":"2305.19798","title":"Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation","created":"2023-05-31","cited_by_count":29},{"id":"2312.17210","title":"Continual Learning via Sequential Function-Space Variational Inference","created":"2023-12-28","cited_by_count":29},{"id":"2007.14846","title":"An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosis","created":"2020-07-26","cited_by_count":22},{"id":"2303.02444","title":"Calibrating Transformers via Sparse Gaussian Processes","created":"2023-03-04","cited_by_count":21},{"id":"2312.17162","title":"Function-Space Regularization in Neural Networks: A Probabilistic Perspective","created":"2023-12-28","cited_by_count":20},{"id":"2105.14594","title":"Sparse Uncertainty Representation in Deep Learning with Inducing Weights","created":"2021-05-30","cited_by_count":16},{"id":"2206.11468","title":"Modular Conformal Calibration","created":"2022-06-23","cited_by_count":15},{"id":"2311.15990","title":"Should We Learn Most Likely Functions or Parameters?","created":"2023-11-27","cited_by_count":12},{"id":"2502.20525","title":"Revisiting Kernel Attention with Correlated Gaussian Process Representation","created":"2025-02-27","cited_by_count":10},{"id":"2312.00794","title":"Informative Priors Improve the Reliability of Multimodal Clinical Data Classification","created":"2023-11-17","cited_by_count":6},{"id":"2402.01476","title":"Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes","created":"2024-02-02","cited_by_count":5},{"id":"1604.01662","title":"A Survey on Bayesian Deep Learning","created":"2016-04-06","cited_by_count":2}],"next_cursor":null}