{"total":82,"rows":[{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228,"area":null},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764,"area":null},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343,"area":null},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2206.08720","title":"Fast Finite Width Neural Tangent Kernel","created":"2022-06-17","cited_by_count":62,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2305.17212","title":"Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks","created":"2023-05-26","cited_by_count":53,"area":null},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52,"area":null},{"id":"2210.04195","title":"Online Training Through Time for Spiking Neural Networks","created":"2022-10-09","cited_by_count":49,"area":null},{"id":"2102.08098","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","created":"2021-02-16","cited_by_count":44,"area":null},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2110.04369","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","created":"2021-10-08","cited_by_count":40,"area":null},{"id":"2203.16102","title":"Continual Normalization: Rethinking Batch Normalization for Online Continual Learning","created":"2022-03-30","cited_by_count":40,"area":null},{"id":"2302.14311","title":"Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks","created":"2023-02-28","cited_by_count":37,"area":null},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"area":null},{"id":"2105.13343","title":"Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error","created":"2021-05-27","cited_by_count":33,"area":null},{"id":"2206.08900","title":"Adapting the Linearised Laplace Model Evidence for Modern Deep Learning","created":"2022-06-17","cited_by_count":29,"area":null},{"id":"2203.08120","title":"Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers","created":"2022-03-15","cited_by_count":28,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"area":null},{"id":"2207.01156","title":"Removing Batch Normalization Boosts Adversarial Training","created":"2022-07-04","cited_by_count":24,"area":null},{"id":"2102.07227","title":"Learning by Turning: Neural Architecture Aware Optimisation","created":"2021-02-14","cited_by_count":23,"area":null},{"id":"2205.14962","title":"Sampling-free Inference for Ab-Initio Potential Energy Surface Networks","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2206.06929","title":"Scaling ResNets in the Large-depth Regime","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2104.08215","title":"\"BNN - BN = ?\": Training Binary Neural Networks without Batch Normalization","created":"2021-04-16","cited_by_count":17,"area":null},{"id":"2403.14737","title":"FedMef: Towards Memory-efficient Federated Dynamic Pruning","created":"2024-03-21","cited_by_count":14,"area":null},{"id":"2302.04907","title":"Binarized Neural Machine Translation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2512.10938","title":"Stronger Normalization-Free Transformers","created":"2025-12-11","cited_by_count":13,"area":null},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2312.12474","title":"Principled Weight Initialisation for Input-Convex Neural Networks","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2306.05879","title":"FedWon: Triumphing Multi-domain Federated Learning Without Normalization","created":"2023-06-09","cited_by_count":11,"area":null},{"id":"2203.03304","title":"Regularising for invariance to data augmentation improves supervised learning","created":"2022-03-07","cited_by_count":9,"area":null},{"id":"2211.06607","title":"Few-shot Multimodal Sentiment Analysis based on Multimodal Probabilistic Fusion Prompts","created":"2022-11-12","cited_by_count":9,"area":null},{"id":"2302.00232","title":"SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","cited_by_count":7,"area":null},{"id":"2302.06112","title":"How to Use Dropout Correctly on Residual Networks with Batch Normalization","created":"2023-02-13","cited_by_count":7,"area":null},{"id":"2106.03640","title":"Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training","created":"2021-06-07","cited_by_count":6,"area":null},{"id":"2112.02834","title":"A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2312.00313","title":"Improving Normalization with the James-Stein Estimator","created":"2023-12-01","cited_by_count":6,"area":null},{"id":"2410.15042","title":"Adversarial Training: A Survey","created":"2024-10-19","cited_by_count":6,"area":null},{"id":"2410.18408","title":"Scale Propagation Network for Generalizable Depth Completion","created":"2024-10-24","cited_by_count":6,"area":null},{"id":"2505.22014","title":"Learning in Compact Spaces with Approximately Normalized Transformer","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2109.08958","title":"AutoInit: Analytic Signal-Preserving Weight Initialization for Neural Networks","created":"2021-09-18","cited_by_count":5,"area":null},{"id":"2204.00826","title":"Online Convolutional Re-parameterization","created":"2022-04-02","cited_by_count":5,"area":null},{"id":"2403.03739","title":"A&B BNN: Add&Bit-Operation-Only Hardware-Friendly Binary Neural Network","created":"2024-03-06","cited_by_count":5,"area":null},{"id":"2105.13890","title":"Towards Efficient Full 8-bit Integer DNN Online Training on Resource-limited Devices without Batch Normalization","created":"2021-05-27","cited_by_count":4,"area":null},{"id":"2210.11407","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2503.21708","title":"On the Mathematical Relationship Between Layer Normalization and Dynamic Activation Functions","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2208.00338","title":"Symmetry Regularization and Saturating Nonlinearity for Robust Quantization","created":"2022-07-31","cited_by_count":3,"area":null},{"id":"2304.04664","title":"Inductive biases in deep learning models for weather prediction","created":"2023-04-06","cited_by_count":3,"area":null},{"id":"2407.12516","title":"Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks","created":"2024-07-17","cited_by_count":3,"area":null},{"id":"2205.10089","title":"Kernel Normalized Convolutional Networks","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2210.06932","title":"NoMorelization: Building Normalizer-Free Models from a Sample's Perspective","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2301.10750","title":"Out of Distribution Performance of State of Art Vision Model","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2310.04412","title":"FedConv: Enhancing Convolutional Neural Networks for Handling Data Heterogeneity in Federated Learning","created":"2023-10-06","cited_by_count":2,"area":null},{"id":"2112.12299","title":"A Robust Initialization of Residual Blocks for Effective ResNet Training without Batch Normalization","created":"2021-12-23","cited_by_count":1,"area":null},{"id":"2205.07260","title":"Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks","created":"2022-05-15","cited_by_count":1,"area":null},{"id":"2211.08486","title":"Scalar Invariant Networks with Zero Bias","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2311.14625","title":"ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2410.03499","title":"FedStein: Enhancing Multi-Domain Federated Learning Through James-Stein Estimator","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2508.16937","title":"NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2512.22657","title":"Investigating Deep Learning Models for Ejection Fraction Estimation from Echocardiography Videos","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2609.03589","title":"Correlated initialization of deep residual networks","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2107.04458","title":"Understanding the Distributions of Aggregation Layers in Deep Neural Networks","created":"2021-07-09","cited_by_count":0,"area":null},{"id":"2210.02411","title":"Dynamical Isometry for Residual Networks","created":"2022-10-05","cited_by_count":0,"area":null},{"id":"2210.17079","title":"FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2304.03374","title":"Optimizing Neural Networks through Activation Function Discovery and Automatic Weight Initialization","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2304.06959","title":"Convex Dual Theory Analysis of Two-Layer Convolutional Neural Networks with Soft-Thresholding","created":"2023-04-14","cited_by_count":0,"area":null},{"id":"2403.05532","title":"Twin: Tuning Learning Rate and Weight Decay of Deep Homogeneous Classifiers without Validation","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2410.02006","title":"An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2508.12609","title":"A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2510.11182","title":"Generalisation of automatic tumour segmentation in histopathological whole-slide images across multiple cancer types","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2512.10522","title":"Disentangled and Distilled Encoder for Out-of-Distribution Reasoning with Rademacher Guarantees","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.17189","title":"Rethinking Benchmarks for Differentially Private Image Classification","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2606.02927","title":"SaluNet: Enabling Total Plasticity in Normalization-Free Deep Networks","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.31695","title":"Intrinsically Stable Spiking Neural Networks: Overcoming the Performance Barrier in the Absence of Batch Normalization","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}