{"list":"other","total":52,"rows":[{"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"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":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"1811.08585","title":"Progressive Feature Alignment for Unsupervised Domain Adaptation","created":"2018-11-21","cited_by_count":183},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"1312.6082","title":"Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks","created":"2013-12-20","cited_by_count":84},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64},{"id":"1901.11058","title":"HyperGAN: A Generative Model for Diverse, Performant Neural Networks","created":"2019-01-30","cited_by_count":51},{"id":"2402.13144","title":"Neural Network Diffusion","created":"2024-02-20","cited_by_count":42},{"id":"2406.09997","title":"Towards Scalable and Versatile Weight Space Learning","created":"2024-06-14","cited_by_count":41},{"id":"2202.12219","title":"Debugging Differential Privacy: A Case Study for Privacy Auditing","created":"2022-02-24","cited_by_count":40},{"id":"2307.16424","title":"MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning","created":"2023-07-31","cited_by_count":40},{"id":"2402.18153","title":"Diffusion-Based Neural Network Weights Generation","created":"2024-02-28","cited_by_count":39},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36},{"id":"2202.03038","title":"Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry","created":"2022-02-07","cited_by_count":28},{"id":"2402.04081","title":"Improved Generalization of Weight Space Networks via Augmentations","created":"2024-02-06","cited_by_count":24},{"id":"2305.13404","title":"Improving Convergence and Generalization Using Parameter Symmetries","created":"2023-05-22","cited_by_count":23},{"id":"2405.20231","title":"The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof","created":"2024-05-30","cited_by_count":21},{"id":"2406.01461","title":"Hardness of Learning Neural Networks under the Manifold Hypothesis","created":"2024-06-03","cited_by_count":18},{"id":"2505.22697","title":"Update Your Transformer to the Latest Release: Re-Basin of Task Vectors","created":"2025-05-28","cited_by_count":17},{"id":"2501.11587","title":"Recurrent Diffusion for Large-Scale Parameter Generation","created":"2025-01-20","cited_by_count":15},{"id":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14},{"id":"1511.03688","title":"Online Principal Component Analysis in High Dimension: Which Algorithm to Choose?","created":"2015-11-11","cited_by_count":12},{"id":"2210.08942","title":"Meta-Learning via Classifier(-free) Diffusion Guidance","created":"2022-10-17","cited_by_count":9},{"id":"2010.05625","title":"Post-Training BatchNorm Recalibration","created":"2020-10-12","cited_by_count":4},{"id":"2306.12949","title":"On the use of the Gram matrix for multivariate functional principal components analysis","created":"2023-06-22","cited_by_count":2},{"id":"2311.08851","title":"Data Augmentations in Deep Weight Spaces","created":"2023-11-15","cited_by_count":2},{"id":"2507.10623","title":"Flows and Diffusions on the Neural Manifold","created":"2025-07-14","cited_by_count":1}],"next_cursor":null}