{"total":47,"rows":[{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"area":null},{"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":"2309.16620","title":"Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit","created":"2023-09-28","cited_by_count":66,"area":null},{"id":"2502.05795","title":"The Curse of Depth in Large Language Models","created":"2025-02-09","cited_by_count":62,"area":null},{"id":"2110.12690","title":"A Dynamical System Perspective for Lipschitz Neural Networks","created":"2021-10-25","cited_by_count":60,"area":null},{"id":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2306.17759","title":"The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit","created":"2023-06-30","cited_by_count":47,"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":"2206.02768","title":"The Neural Covariance SDE: Shaped Infinite Depth-and-Width Networks at Initialization","created":"2022-06-06","cited_by_count":41,"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":"2203.08120","title":"Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers","created":"2022-03-15","cited_by_count":28,"area":null},{"id":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2210.00688","title":"On the infinite-depth limit of finite-width neural networks","created":"2022-10-03","cited_by_count":22,"area":null},{"id":"2104.03093","title":"Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks","created":"2021-04-07","cited_by_count":21,"area":null},{"id":"2302.00453","title":"Width and Depth Limits Commute in Residual Networks","created":"2023-02-01","cited_by_count":21,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2206.06929","title":"Scaling ResNets in the Large-depth Regime","created":"2022-06-14","cited_by_count":18,"area":null},{"id":"2509.10167","title":"The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagram","created":"2025-09-12","cited_by_count":17,"area":null},{"id":"2310.10767","title":"Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models","created":"2023-10-16","cited_by_count":14,"area":null},{"id":"2505.01996","title":"Always Skip Attention","created":"2025-05-04","cited_by_count":13,"area":null},{"id":"2407.14885","title":"Falcon2-11B Technical Report","created":"2024-07-20","cited_by_count":12,"area":null},{"id":"2311.18718","title":"The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2106.09798","title":"Wide stochastic networks: Gaussian limit and PAC-Bayesian training","created":"2021-06-17","cited_by_count":10,"area":null},{"id":"2405.19279","title":"Understanding and Minimising Outlier Features in Neural Network Training","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2601.21942","title":"Clustering in Deep Stochastic Transformers","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2106.03091","title":"Regularization in ResNet with Stochastic Depth","created":"2021-06-06","cited_by_count":7,"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":"2506.15025","title":"Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size","created":"2025-06-17","cited_by_count":6,"area":null},{"id":"2506.16884","title":"The Importance of Being Lazy: Scaling Limits of Continual Learning","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2310.12079","title":"Differential Equation Scaling Limits of Shaped and Unshaped Neural Networks","created":"2023-10-18","cited_by_count":4,"area":null},{"id":"2204.05891","title":"A DNN Framework for Learning Lagrangian Drift With Uncertainty","created":"2022-04-12","cited_by_count":3,"area":null},{"id":"2204.08528","title":"An Optimal Time Variable Learning Framework for Deep Neural Networks","created":"2022-04-18","cited_by_count":3,"area":null},{"id":"2403.09889","title":"Generalization of Scaled Deep ResNets in the Mean-Field Regime","created":"2024-03-14","cited_by_count":3,"area":null},{"id":"2511.01734","title":"A Proof of Learning Rate Transfer under $\\mu$P","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2602.07697","title":"On the Infinite Width and Depth Limits of Predictive Coding Networks","created":"2026-02-07","cited_by_count":2,"area":null},{"id":"2607.14018","title":"Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2310.01683","title":"Commutative Width and Depth Scaling in Deep Neural Networks","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2312.13259","title":"A note on regularised NTK dynamics with an application to PAC-Bayesian training","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2605.18870","title":"Multi-Headed Transformer Architectures as Time-dependent Wasserstein Gradient Flows","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2509.20734","title":"Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Induction","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2602.10949","title":"Optimal Initialization in Depth: Lyapunov Initialization and Limit Theorems for Deep Leaky ReLU Networks","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.15742","title":"Collective Kernel EFT for Pre-activation ResNets","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2606.30831","title":"Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2609.09244","title":"Critical initialization destabilizes higher input derivatives in wide scalar-input networks","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.30633","title":"Stable initialization without the CLT","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}