{"total":34,"rows":[{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2103.17268","title":"Fast Certified Robust Training with Short Warmup","created":"2021-03-31","cited_by_count":46,"area":null},{"id":"2302.10322","title":"Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation","created":"2023-02-20","cited_by_count":45,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2106.04013","title":"The Future is Log-Gaussian: ResNets and Their Infinite-Depth-and-Width Limit at Initialization","created":"2021-06-07","cited_by_count":33,"area":null},{"id":"2206.06929","title":"Scaling ResNets in the Large-depth Regime","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2405.13456","title":"Deep linear networks for regression are implicitly regularized towards flat minima","created":"2024-05-22","cited_by_count":17,"area":null},{"id":"2406.17503","title":"WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models","created":"2024-06-25","cited_by_count":17,"area":null},{"id":"2301.12309","title":"On the Lipschitz Constant of Deep Networks and Double Descent","created":"2023-01-28","cited_by_count":11,"area":null},{"id":"2404.16897","title":"Exploring Learngene via Stage-wise Weight Sharing for Initializing Variable-sized Models","created":"2024-04-25","cited_by_count":9,"area":null},{"id":"2409.01696","title":"On the Vulnerability of Skip Connections to Model Inversion Attacks","created":"2024-09-03","cited_by_count":9,"area":null},{"id":"2209.10080","title":"Deep Double Descent via Smooth Interpolation","created":"2022-09-21","cited_by_count":8,"area":null},{"id":"2307.07512","title":"Expressive Monotonic Neural Networks","created":"2023-07-14","cited_by_count":7,"area":null},{"id":"2112.00038","title":"Robust and Provably Monotonic Networks","created":"2021-11-30","cited_by_count":6,"area":null},{"id":"2301.04608","title":"Padding Module: Learning the Padding in Deep Neural Networks","created":"2023-01-11","cited_by_count":6,"area":null},{"id":"2305.07715","title":"Field theory for optimal signal propagation in ResNets","created":"2023-05-12","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":"2306.00809","title":"Initial Guessing Bias: How Untrained Networks Favor Some Classes","created":"2023-06-01","cited_by_count":5,"area":null},{"id":"2307.01199","title":"NeuBTF: Neural fields for BTF encoding and transfer","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2503.04626","title":"IDInit: A Universal and Stable Initialization Method for Neural Network Training","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2209.01083","title":"When Bioprocess Engineering Meets Machine Learning: A Survey from the Perspective of Automated Bioprocess Development","created":"2022-09-02","cited_by_count":4,"area":null},{"id":"2401.10178","title":"Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields","created":"2024-01-18","cited_by_count":4,"area":null},{"id":"2109.00125","title":"A Weight Initialization Based on the Linear Product Structure for Neural Networks","created":"2021-09-01","cited_by_count":2,"area":null},{"id":"2212.12086","title":"Eigenvalue initialisation and regularisation for Koopman autoencoders","created":"2022-12-23","cited_by_count":2,"area":null},{"id":"2305.08879","title":"Spiking Network Initialisation and Firing Rate Collapse","created":"2023-05-13","cited_by_count":2,"area":null},{"id":"2409.12034","title":"Multi-Sensor Deep Learning for Glacier Mapping","created":"2024-09-18","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":"2609.03589","title":"Correlated initialization of deep residual networks","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2303.00788","title":"Multi-task neural networks by learned contextual inputs","created":"2023-03-01","cited_by_count":0,"area":null},{"id":"2508.12834","title":"Optimal Condition for Initialization Variance in Deep Neural Networks: An SGD Dynamics Perspective","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2510.04327","title":"Arithmetic-Mean $\\mu$P for Modern Architectures: A Unified Learning-Rate Scale for CNNs and ResNets","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2604.14769","title":"Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2607.14233","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","created":"2026-07-15","cited_by_count":0,"area":null}],"next_cursor":null}