{"total":203,"rows":[{"id":"2106.14806","title":"Laplace Redux -- Effortless Bayesian Deep Learning","created":"2021-06-28","cited_by_count":365,"area":null},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308,"area":null},{"id":"2305.05644","title":"Towards Building the Federated GPT: Federated Instruction Tuning","created":"2023-05-09","cited_by_count":185,"area":null},{"id":"2102.06571","title":"Bayesian Neural Network Priors Revisited","created":"2021-02-12","cited_by_count":121,"area":null},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115,"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":"2105.06868","title":"Priors in Bayesian Deep Learning: A Review","created":"2021-05-14","cited_by_count":101,"area":null},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2102.12108","title":"The Promises and Pitfalls of Deep Kernel Learning","created":"2021-02-24","cited_by_count":81,"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":"2402.00809","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","created":"2024-02-01","cited_by_count":62,"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":"2406.11675","title":"BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models","created":"2024-06-17","cited_by_count":50,"area":null},{"id":"2101.05544","title":"DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation","created":"2021-01-14","cited_by_count":48,"area":null},{"id":"2203.16481","title":"On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification","created":"2022-03-30","cited_by_count":46,"area":null},{"id":"2206.09914","title":"A Langevin-like Sampler for Discrete Distributions","created":"2022-06-20","cited_by_count":44,"area":null},{"id":"2205.10279","title":"Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors","created":"2022-05-20","cited_by_count":43,"area":null},{"id":"2402.12264","title":"Uncertainty quantification in fine-tuned LLMs using LoRA ensembles","created":"2024-02-19","cited_by_count":37,"area":null},{"id":"2106.05586","title":"Data augmentation in Bayesian neural networks and the cold posterior effect","created":"2021-06-10","cited_by_count":36,"area":null},{"id":"2310.11142","title":"BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference","created":"2023-10-17","cited_by_count":35,"area":"diffusion"},{"id":"2402.13210","title":"Bayesian Reward Models for LLM Alignment","created":"2024-02-20","cited_by_count":35,"area":"alignment"},{"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":"2209.15245","title":"Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2302.05086","title":"Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples","created":"2023-02-10","cited_by_count":32,"area":null},{"id":"2102.01691","title":"Exact Langevin Dynamics with Stochastic Gradients","created":"2021-02-02","cited_by_count":30,"area":null},{"id":"2210.12642","title":"Accelerated Linearized Laplace Approximation for Bayesian Deep Learning","created":"2022-10-23","cited_by_count":28,"area":null},{"id":"2307.03217","title":"Quantification of Uncertainty with Adversarial Models","created":"2023-07-06","cited_by_count":28,"area":null},{"id":"2311.08309","title":"Introducing an Improved Information-Theoretic Measure of Predictive Uncertainty","created":"2023-11-14","cited_by_count":28,"area":null},{"id":"2206.14502","title":"RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustness","created":"2022-06-29","cited_by_count":27,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2101.09815","title":"Annealed Stein Variational Gradient Descent","created":"2021-01-24","cited_by_count":26,"area":null},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25,"area":null},{"id":"2202.13585","title":"Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten","created":"2022-02-28","cited_by_count":25,"area":"safety"},{"id":"2208.01565","title":"Approximate Bayesian Neural Operators: Uncertainty Quantification for Parametric PDEs","created":"2022-08-02","cited_by_count":25,"area":null},{"id":"2111.01968","title":"A Survey on Epistemic (Model) Uncertainty in Supervised Learning: Recent Advances and Applications","created":"2021-11-03","cited_by_count":24,"area":null},{"id":"2211.10575","title":"Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constants","created":"2022-11-19","cited_by_count":24,"area":null},{"id":"2106.06596","title":"Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect","created":"2021-06-11","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":"2203.12964","title":"Knowledge Removal in Sampling-based Bayesian Inference","created":"2022-03-24","cited_by_count":21,"area":"safety"},{"id":"2303.02444","title":"Calibrating Transformers via Sparse Gaussian Processes","created":"2023-03-04","cited_by_count":21,"area":null},{"id":"2105.06964","title":"BNNpriors: A library for Bayesian neural network inference with different prior distributions","created":"2021-05-14","cited_by_count":20,"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":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"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":"2105.14594","title":"Sparse Uncertainty Representation in Deep Learning with Inducing Weights","created":"2021-05-30","cited_by_count":16,"area":null},{"id":"2106.03904","title":"When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting","created":"2021-06-07","cited_by_count":16,"area":null},{"id":"2410.10786","title":"On Information-Theoretic Measures of Predictive Uncertainty","created":"2024-10-14","cited_by_count":16,"area":null},{"id":"2411.02433","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","created":"2024-11-01","cited_by_count":16,"area":"moe"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2104.11667","title":"Deep Learning for Bayesian Optimization of Scientific Problems with High-Dimensional Structure","created":"2021-04-23","cited_by_count":15,"area":null},{"id":"2106.10065","title":"Being a Bit Frequentist Improves Bayesian Neural Networks","created":"2021-06-18","cited_by_count":15,"area":null},{"id":"2205.10041","title":"Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks","created":"2022-05-20","cited_by_count":14,"area":null},{"id":"2110.04020","title":"Pathologies in priors and inference for Bayesian transformers","created":"2021-10-08","cited_by_count":13,"area":null},{"id":"2205.08187","title":"Deep neural networks with dependent weights: Gaussian Process mixture limit, heavy tails, sparsity and compressibility","created":"2022-05-17","cited_by_count":13,"area":null},{"id":"2205.13900","title":"How Tempering Fixes Data Augmentation in Bayesian Neural Networks","created":"2022-05-27","cited_by_count":13,"area":null},{"id":"2209.12330","title":"Personalizing Text-to-Image Generation via Aesthetic Gradients","created":"2022-09-25","cited_by_count":13,"area":"diffusion"},{"id":"2406.00104","title":"Scalable Bayesian Learning with posteriors","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2410.19780","title":"Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics","created":"2024-10-14","cited_by_count":13,"area":null},{"id":"2107.09028","title":"Structured Stochastic Gradient MCMC","created":"2021-07-19","cited_by_count":12,"area":null},{"id":"2205.14283","title":"Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling","created":"2022-05-28","cited_by_count":12,"area":null},{"id":"2206.07562","title":"Federated Learning with Uncertainty via Distilled Predictive Distributions","created":"2022-06-15","cited_by_count":12,"area":null},{"id":"2206.09909","title":"Low-Precision Stochastic Gradient Langevin Dynamics","created":"2022-06-20","cited_by_count":12,"area":null},{"id":"2310.08287","title":"A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors","created":"2023-10-12","cited_by_count":12,"area":null},{"id":"2311.01046","title":"Time-Independent Information-Theoretic Generalization Bounds for SGLD","created":"2023-11-02","cited_by_count":12,"area":null},{"id":"2406.05072","title":"Linearization Turns Neural Operators into Function-Valued Gaussian Processes","created":"2024-06-07","cited_by_count":12,"area":null},{"id":"2105.13937","title":"Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks","created":"2021-05-28","cited_by_count":11,"area":null},{"id":"2203.08272","title":"Active Exploration for Neural Global Illumination of Variable Scenes","created":"2022-03-15","cited_by_count":11,"area":null},{"id":"2204.09389","title":"Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation","created":"2022-04-20","cited_by_count":11,"area":null},{"id":"2210.06447","title":"Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2212.07959","title":"Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls","created":"2022-12-15","cited_by_count":11,"area":null},{"id":"2308.10544","title":"Towards Accelerated Model Training via Bayesian Data Selection","created":"2023-08-21","cited_by_count":11,"area":null},{"id":"2106.06245","title":"Model Selection for Bayesian Autoencoders","created":"2021-06-11","cited_by_count":10,"area":null},{"id":"2312.09817","title":"Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space","created":"2023-12-15","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":"2410.09697","title":"Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics","created":"2024-10-13","cited_by_count":10,"area":null},{"id":"2502.06335","title":"Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2106.06997","title":"Post-hoc loss-calibration for Bayesian neural networks","created":"2021-06-13","cited_by_count":9,"area":null},{"id":"2202.09867","title":"Interacting Contour Stochastic Gradient Langevin Dynamics","created":"2022-02-20","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":"2211.09283","title":"Active Learning with Expected Error Reduction","created":"2022-11-17","cited_by_count":9,"area":null},{"id":"2302.04534","title":"Fully Bayesian Autoencoders with Latent Sparse Gaussian Processes","created":"2023-02-09","cited_by_count":9,"area":null},{"id":"2305.14765","title":"Masked Bayesian Neural Networks : Theoretical Guarantee and its Posterior Inference","created":"2023-05-24","cited_by_count":9,"area":null},{"id":"2402.17699","title":"Gradient-based Discrete Sampling with Automatic Cyclical Scheduling","created":"2024-02-27","cited_by_count":9,"area":null},{"id":"2403.12729","title":"Posterior Uncertainty Quantification in Neural Networks using Data Augmentation","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2503.16218","title":"Temporal Score Analysis for Understanding and Correcting Diffusion Artifacts","created":"2025-03-20","cited_by_count":9,"area":"diffusion"},{"id":"2505.17773","title":"C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2206.02435","title":"Tackling covariate shift with node-based Bayesian neural networks","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2303.05101","title":"Scalable Stochastic Gradient Riemannian Langevin Dynamics in Non-Diagonal Metrics","created":"2023-03-09","cited_by_count":8,"area":null},{"id":"2403.02251","title":"A prediction rigidity formalism for low-cost uncertainties in trained neural networks","created":"2024-03-04","cited_by_count":8,"area":null},{"id":"2101.06417","title":"Bayesian Inference Forgetting","created":"2021-01-16","cited_by_count":7,"area":null},{"id":"2211.10837","title":"Non-reversible Parallel Tempering for Deep Posterior Approximation","created":"2022-11-20","cited_by_count":7,"area":null},{"id":"2306.02775","title":"Input-gradient space particle inference for neural network ensembles","created":"2023-06-05","cited_by_count":7,"area":null},{"id":"2402.11025","title":"Training Bayesian Neural Networks with Sparse Subspace Variational Inference","created":"2024-02-16","cited_by_count":7,"area":null},{"id":"2405.07839","title":"Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics","created":"2024-05-13","cited_by_count":7,"area":null},{"id":"2602.06500","title":"Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?","created":"2026-02-06","cited_by_count":7,"area":null},{"id":"2302.09574","title":"Guided Deep Kernel Learning","created":"2023-02-19","cited_by_count":6,"area":null},{"id":"2303.03374","title":"To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning","created":"2023-03-06","cited_by_count":6,"area":null},{"id":"2310.00137","title":"On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective","created":"2023-09-29","cited_by_count":6,"area":null}],"next_cursor":"100"}