{"total":15,"rows":[{"id":"2205.00403","title":"A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness","created":"2022-05-01","cited_by_count":49,"area":null},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46,"area":null},{"id":"2105.14417","title":"Overparameterization of deep ResNet: zero loss and mean-field analysis","created":"2021-05-30","cited_by_count":24,"area":null},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16,"area":null},{"id":"2202.08985","title":"Out of Distribution Data Detection Using Dropout Bayesian Neural Networks","created":"2022-02-18","cited_by_count":15,"area":null},{"id":"2302.01952","title":"On a continuous time model of gradient descent dynamics and instability in deep learning","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2202.08070","title":"On Measuring Excess Capacity in Neural Networks","created":"2022-02-16","cited_by_count":9,"area":null},{"id":"2111.15639","title":"DeDUCE: Generating Counterfactual Explanations Efficiently","created":"2021-11-29","cited_by_count":6,"area":null},{"id":"2204.07261","title":"Convergence and Implicit Regularization Properties of Gradient Descent for Deep Residual Networks","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2111.12963","title":"Error Bounds for a Matrix-Vector Product Approximation with Deep ReLU Neural Networks","created":"2021-11-25","cited_by_count":2,"area":null},{"id":"2212.14681","title":"An Entropy-Based Model for Hierarchical Learning","created":"2022-12-30","cited_by_count":2,"area":null},{"id":"2405.04759","title":"Multi-Label Out-of-Distribution Detection with Spectral Normalized Joint Energy","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2505.24469","title":"Smooth Model Compression without Fine-Tuning","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2605.05133","title":"Transformed Latent Variable Multi-Output Gaussian Processes","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2607.07083","title":"Prior-aware and Context-guided Group Sampling for Active Probabilistic Subsampling","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}