{"list":"other","total":51,"rows":[{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1601.00670","title":"Variational Inference: A Review for Statisticians","created":"2016-01-04","cited_by_count":1472},{"id":"1412.1897","title":"Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images","created":"2014-12-05","cited_by_count":776},{"id":"1711.00165","title":"Deep Neural Networks as Gaussian Processes","created":"2017-11-01","cited_by_count":622},{"id":"2007.06823","title":"Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Users","created":"2020-07-14","cited_by_count":338},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"1804.11271","title":"Gaussian Process Behaviour in Wide Deep Neural Networks","created":"2018-04-30","cited_by_count":317},{"id":"1711.05597","title":"Advances in Variational Inference","created":"2017-11-15","cited_by_count":236},{"id":"2002.06470","title":"Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning","created":"2020-02-15","cited_by_count":210},{"id":"1912.11554","title":"Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro","created":"2019-12-24","cited_by_count":191},{"id":"2305.12082","title":"SneakyPrompt: Jailbreaking Text-to-image Generative Models","created":"2023-05-20","cited_by_count":189},{"id":"2305.20009","title":"Protein Design with Guided Discrete Diffusion","created":"2023-05-31","cited_by_count":157},{"id":"1602.05897","title":"Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity","created":"2016-02-18","cited_by_count":138},{"id":"1706.09293","title":"Concentration of tempered posteriors and of their variational approximations","created":"2017-06-28","cited_by_count":66},{"id":"1705.03439","title":"Frequentist Consistency of Variational Bayes","created":"2017-05-09","cited_by_count":60},{"id":"1802.02538","title":"Yes, but Did It Work?: Evaluating Variational Inference","created":"2018-02-07","cited_by_count":53},{"id":"1803.09138","title":"Posterior Concentration for Sparse Deep Learning","created":"2018-03-24","cited_by_count":50},{"id":"2002.04359","title":"Robustness of Bayesian Neural Networks to Gradient-Based Attacks","created":"2020-02-11","cited_by_count":48},{"id":"1712.02519","title":"Convergence Rates of Variational Posterior Distributions","created":"2017-12-07","cited_by_count":45},{"id":"1904.07150","title":"Variational Bayes for high-dimensional linear regression with sparse priors","created":"2019-04-15","cited_by_count":44},{"id":"2011.07439","title":"Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee","created":"2020-11-15","cited_by_count":37},{"id":"1806.05975","title":"Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors","created":"2018-06-13","cited_by_count":35},{"id":"2006.12335","title":"Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriors","created":"2020-06-22","cited_by_count":29},{"id":"1908.04847","title":"Convergence Rates of Variational Inference in Sparse Deep Learning","created":"2019-08-09","cited_by_count":27},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27},{"id":"2310.01651","title":"Fool Your (Vision and) Language Model With Embarrassingly Simple Permutations","created":"2023-10-02","cited_by_count":25},{"id":"2003.00394","title":"Stable behaviour of infinitely wide deep neural networks","created":"2020-03-01","cited_by_count":23},{"id":"2202.11670","title":"Wide Mean-Field Bayesian Neural Networks Ignore the Data","created":"2022-02-23","cited_by_count":22},{"id":"2001.00921","title":"Wide Neural Networks with Bottlenecks are Deep Gaussian Processes","created":"2020-01-03","cited_by_count":20},{"id":"2306.01122","title":"On the Convergence of Coordinate Ascent Variational Inference","created":"2023-06-01","cited_by_count":18},{"id":"2109.03204","title":"Adaptive variational Bayes: Optimality, computation and applications","created":"2021-09-07","cited_by_count":17},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11},{"id":"1610.05559","title":"On the Hyperprior Choice for the Global Shrinkage Parameter in the Horseshoe Prior","created":"2016-10-18","cited_by_count":10},{"id":"1711.06999","title":"Conditionally conjugate mean-field variational Bayes for logistic models","created":"2017-11-19","cited_by_count":10},{"id":"2307.15073","title":"Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions","created":"2023-07-14","cited_by_count":10},{"id":"2406.03369","title":"Posterior and variational inference for deep neural networks with heavy-tailed weights","created":"2024-06-05","cited_by_count":10},{"id":"1408.0464","title":"Decoupling shrinkage and selection in Bayesian linear models: a posterior summary perspective","created":"2014-08-03","cited_by_count":8},{"id":"1810.02406","title":"Projective Inference in High-dimensional Problems: Prediction and Feature Selection","created":"2018-10-04","cited_by_count":8},{"id":"2206.00241","title":"Asymptotic Properties for Bayesian Neural Network in Besov Space","created":"2022-06-01","cited_by_count":7},{"id":"2012.10943","title":"Trace-class Gaussian priors for Bayesian learning of neural networks with MCMC","created":"2020-12-20","cited_by_count":5},{"id":"1503.04303","title":"Variable Selection Using Shrinkage Priors","created":"2015-03-14","cited_by_count":3},{"id":"2111.14397","title":"Dependence between Bayesian neural network units","created":"2021-11-29","cited_by_count":3},{"id":"2010.13229","title":"Latent Network Estimation and Variable Selection for Compositional Data via Variational EM","created":"2020-10-25","cited_by_count":1},{"id":"2102.11010","title":"Resilience of Bayesian Layer-Wise Explanations under Adversarial Attacks","created":"2021-02-22","cited_by_count":1},{"id":"2402.12323","title":"Expressing and visualizing model uncertainty in Bayesian variable selection using Cartesian credible sets","created":"2024-02-19","cited_by_count":1}],"next_cursor":null}