{"total":159,"rows":[{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360,"area":null},{"id":"2212.07555","title":"IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions","created":"2022-12-14","cited_by_count":124,"area":null},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"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":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73,"area":null},{"id":"2503.10622","title":"Transformers without Normalization","created":"2025-03-13","cited_by_count":70,"area":null},{"id":"2210.05337","title":"SGD with Large Step Sizes Learns Sparse Features","created":"2022-10-11","cited_by_count":68,"area":null},{"id":"2406.07456","title":"fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions","created":"2024-06-11","cited_by_count":64,"area":null},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2206.10654","title":"On the Maximum Hessian Eigenvalue and Generalization","created":"2022-06-21","cited_by_count":57,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2105.02716","title":"Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks","created":"2021-05-06","cited_by_count":50,"area":null},{"id":"2206.06072","title":"Rank Diminishing in Deep Neural Networks","created":"2022-06-13","cited_by_count":47,"area":null},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46,"area":null},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43,"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":"2106.03970","title":"Batch Normalization Orthogonalizes Representations in Deep Random Networks","created":"2021-06-07","cited_by_count":29,"area":null},{"id":"2110.11222","title":"Is High Variance Unavoidable in RL? A Case Study in Continuous Control","created":"2021-10-21","cited_by_count":28,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2306.04226","title":"Normalization Layers Are All That Sharpness-Aware Minimization Needs","created":"2023-06-07","cited_by_count":27,"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":"2103.01499","title":"Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization","created":"2021-03-02","cited_by_count":21,"area":null},{"id":"2109.01657","title":"A Multi-view Multi-task Learning Framework for Multi-variate Time Series Forecasting","created":"2021-09-02","cited_by_count":21,"area":null},{"id":"2106.15739","title":"On the Periodic Behavior of Neural Network Training with Batch Normalization and Weight Decay","created":"2021-06-29","cited_by_count":20,"area":null},{"id":"2203.07976","title":"On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2201.12559","title":"Rebalancing Batch Normalization for Exemplar-based Class-Incremental Learning","created":"2022-01-29","cited_by_count":16,"area":null},{"id":"2203.04737","title":"P2M: A Processing-in-Pixel-in-Memory Paradigm for Resource-Constrained TinyML Applications","created":"2022-03-07","cited_by_count":16,"area":null},{"id":"2407.13771","title":"Training-Free Model Merging for Multi-target Domain Adaptation","created":"2024-07-18","cited_by_count":15,"area":null},{"id":"2304.07645","title":"Magnitude Invariant Parametrizations Improve Hypernetwork Learning","created":"2023-04-15","cited_by_count":14,"area":null},{"id":"2302.07937","title":"The Expressive Power of Tuning Only the Normalization Layers","created":"2023-02-15","cited_by_count":13,"area":null},{"id":"2305.18399","title":"On the impact of activation and normalization in obtaining isometric embeddings at initialization","created":"2023-05-28","cited_by_count":13,"area":null},{"id":"2306.00656","title":"Normalization Enhances Generalization in Visual Reinforcement Learning","created":"2023-06-01","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":"2210.05153","title":"Understanding the Failure of Batch Normalization for Transformers in NLP","created":"2022-10-11","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":"2310.08855","title":"Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation","created":"2023-10-13","cited_by_count":11,"area":null},{"id":"2404.02113","title":"Position: Lifetime tuning is incompatible with continual reinforcement learning","created":"2024-04-02","cited_by_count":11,"area":"deeprl"},{"id":"2403.17410","title":"On permutation-invariant neural networks","created":"2024-03-26","cited_by_count":10,"area":null},{"id":"2407.05128","title":"SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention","created":"2024-07-06","cited_by_count":10,"area":null},{"id":"2309.04644","title":"Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay","created":"2023-09-09","cited_by_count":9,"area":null},{"id":"2311.11883","title":"Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2406.01255","title":"On the Nonlinearity of Layer Normalization","created":"2024-06-03","cited_by_count":9,"area":null},{"id":"2207.03615","title":"Learning and generalization of one-hidden-layer neural networks, going beyond standard Gaussian data","created":"2022-07-07","cited_by_count":8,"area":null},{"id":"2209.14778","title":"Batch Normalization Explained","created":"2022-09-29","cited_by_count":8,"area":null},{"id":"2303.06530","title":"Making Batch Normalization Great in Federated Deep Learning","created":"2023-03-12","cited_by_count":8,"area":null},{"id":"2306.11680","title":"The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks","created":"2023-06-20","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":"2102.11382","title":"Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity","created":"2021-02-22","cited_by_count":7,"area":null},{"id":"2107.00090","title":"Mesh-based graph convolutional neural networks for modeling materials with microstructure","created":"2021-06-04","cited_by_count":7,"area":null},{"id":"2107.12445","title":"Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression","created":"2021-07-16","cited_by_count":7,"area":null},{"id":"2203.10778","title":"Delving into the Estimation Shift of Batch Normalization in a Network","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2404.13344","title":"GRANOLA: Adaptive Normalization for Graph Neural Networks","created":"2024-04-20","cited_by_count":7,"area":null},{"id":"2307.00592","title":"X-MLP: A Patch Embedding-Free MLP Architecture for Vision","created":"2023-07-02","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":"2106.07879","title":"A Lightweight ReLU-Based Feature Fusion for Aerial Scene Classification","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2108.01110","title":"Batch Normalization Preconditioning for Neural Network Training","created":"2021-08-02","cited_by_count":5,"area":null},{"id":"2505.07300","title":"L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","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":"2208.03720","title":"PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs","created":"2022-08-07","cited_by_count":4,"area":null},{"id":"2303.01300","title":"Compensating for Sensing Failures via Delegation in Human-AI Hybrid Systems","created":"2023-03-02","cited_by_count":4,"area":null},{"id":"2306.00700","title":"On the Weight Dynamics of Deep Normalized Networks","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2311.14993","title":"Coordinate-Aware Modulation for Neural Fields","created":"2023-11-25","cited_by_count":4,"area":null},{"id":"2407.19299","title":"The Impact of LoRA Adapters on LLMs for Clinical Text Classification Under Computational and Data Constraints","created":"2024-07-27","cited_by_count":4,"area":null},{"id":"2106.03763","title":"Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2107.11979","title":"HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification","created":"2021-07-26","cited_by_count":3,"area":null},{"id":"2110.13989","title":"Revisiting Batch Norm Initialization","created":"2021-10-26","cited_by_count":3,"area":null},{"id":"2209.04445","title":"Privacy-Preserving Deep Learning Model for Covid-19 Disease Detection","created":"2022-09-07","cited_by_count":3,"area":null},{"id":"2302.12444","title":"On the Training Instability of Shuffling SGD with Batch Normalization","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2306.01470","title":"Understanding MLP-Mixer as a Wide and Sparse MLP","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2403.06401","title":"Refining Segmentation On-the-Fly: An Interactive Framework for Point Cloud Semantic Segmentation","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2407.03125","title":"Foundations and Frontiers of Graph Learning Theory","created":"2024-07-03","cited_by_count":3,"area":null},{"id":"2502.18277","title":"Self-Adjust Softmax","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2505.22602","title":"One Rank at a Time: Cascading Error Dynamics in Sequential Learning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2603.00439","title":"Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modeling","created":"2026-02-28","cited_by_count":3,"area":"ssm"},{"id":"2104.06307","title":"Detecting False Data Injection Attacks in Smart Grids with Modeling Errors: A Deep Transfer Learning Based Approach","created":"2021-04-09","cited_by_count":2,"area":null},{"id":"2112.00265","title":"Training BatchNorm Only in Neural Architecture Search and Beyond","created":"2021-12-01","cited_by_count":2,"area":null},{"id":"2204.00694","title":"Testing Feedforward Neural Networks Training Programs","created":"2022-04-01","cited_by_count":2,"area":null},{"id":"2205.07372","title":"Effect of Batch Normalization on Noise Resistant Property of Deep Learning Models","created":"2022-05-15","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":"2302.09429","title":"NU-AIR -- A Neuromorphic Urban Aerial Dataset for Detection and Localization of Pedestrians and Vehicles","created":"2023-02-18","cited_by_count":2,"area":null},{"id":"2304.10714","title":"Picking Up Quantization Steps for Compressed Image Classification","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2305.19443","title":"OWAdapt: An adaptive loss function for deep learning using OWA operators","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2310.20327","title":"Improving Entropy-Based Test-Time Adaptation from a Clustering View","created":"2023-10-31","cited_by_count":2,"area":null},{"id":"2404.00521","title":"CHAIN: Enhancing Generalization in Data-Efficient GANs via lipsCHitz continuity constrAIned Normalization","created":"2024-03-31","cited_by_count":2,"area":null},{"id":"2406.05631","title":"CCSI: Continual Class-Specific Impression for Data-free Class Incremental Learning","created":"2024-06-09","cited_by_count":2,"area":null},{"id":"2410.22110","title":"Data Generation for Hardware-Friendly Post-Training Quantization","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2411.00209","title":"Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification","created":"2024-10-31","cited_by_count":2,"area":"distill"},{"id":"2501.09137","title":"Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks","created":"2025-01-15","cited_by_count":2,"area":null},{"id":"2502.15032","title":"GeoAggregator: An Efficient Transformer Model for Geo-Spatial Tabular Data","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2504.01459","title":"Probabilistic Curriculum Learning for Goal-Based Reinforcement Learning","created":"2025-04-02","cited_by_count":2,"area":"deeprl"},{"id":"2508.03183","title":"Spatiotemporal wall pressure forecast of a rectangular cylinder with physics-aware DeepU-Fourier neural network","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2607.06922","title":"Latency-Constrained DNN Architecture Learning for Edge Systems using Zerorized Batch Normalization","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2103.11590","title":"Delving into Variance Transmission and Normalization: Shift of Average Gradient Makes the Network Collapse","created":"2021-03-22","cited_by_count":1,"area":null},{"id":"2110.08725","title":"A Riemannian Mean Field Formulation for Two-layer Neural Networks with Batch Normalization","created":"2021-10-17","cited_by_count":1,"area":null},{"id":"2204.05917","title":"Spatiotemporal Estimation of TROPOMI NO2 Column with Depthwise Partial Convolutional Neural Network","created":"2022-04-12","cited_by_count":1,"area":null},{"id":"2207.08022","title":"Monitoring Vegetation From Space at Extremely Fine Resolutions via Coarsely-Supervised Smooth U-Net","created":"2022-07-16","cited_by_count":1,"area":null},{"id":"2207.14443","title":"A Survey of Learning on Small Data: Generalization, Optimization, and Challenge","created":"2022-07-29","cited_by_count":1,"area":null}],"next_cursor":"100"}