{"total":22,"rows":[{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"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":"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":"2304.03408","title":"Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks","created":"2023-04-06","cited_by_count":43,"area":null},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39,"area":null},{"id":"2309.16314","title":"A Primer on Bayesian Neural Networks: Review and Debates","created":"2023-09-28","cited_by_count":27,"area":null},{"id":"2303.17671","title":"Neural signature kernels as infinite-width-depth-limits of controlled ResNets","created":"2023-03-30","cited_by_count":25,"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":"2302.00453","title":"Width and Depth Limits Commute in Residual Networks","created":"2023-02-01","cited_by_count":21,"area":null},{"id":"2309.01213","title":"Implicit regularization of deep residual networks towards neural ODEs","created":"2023-09-03","cited_by_count":20,"area":null},{"id":"2407.01602","title":"Clustering in pure-attention hardmax transformers and its role in sentiment analysis","created":"2024-06-26","cited_by_count":15,"area":null},{"id":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9,"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":"2307.01177","title":"Neural Hilbert Ladders: Multi-Layer Neural Networks in Function Space","created":"2023-07-03","cited_by_count":5,"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":"2310.01683","title":"Commutative Width and Depth Scaling in Deep Neural Networks","created":"2023-10-02","cited_by_count":1,"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":"2603.05204","title":"Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.12060","title":"Chemical Reaction Networks Learn Better than Spiking Neural Networks","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2606.08218","title":"How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.07884","title":"Optimal Learning Rate Scaling Depends on Data in Deep Scalar Linear Networks","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}