{"total":46,"rows":[{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"area":null},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"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":"2406.08447","title":"The Impact of Initialization on LoRA Finetuning Dynamics","created":"2024-06-12","cited_by_count":54,"area":null},{"id":"2402.04161","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","created":"2024-02-06","cited_by_count":40,"area":null},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39,"area":null},{"id":"2311.01906","title":"Simplifying Transformer Blocks","created":"2023-11-03","cited_by_count":37,"area":null},{"id":"2411.04551","title":"Measure-to-measure interpolation using Transformers","created":"2024-11-07","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2403.02579","title":"Geometric Dynamics of Signal Propagation Predict Trainability of Transformers","created":"2024-03-05","cited_by_count":24,"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":"2505.24333","title":"Two failure modes of deep transformers and how to avoid them: a unified theory of signal propagation at initialisation","created":"2025-05-30","cited_by_count":17,"area":null},{"id":"2510.01098","title":"Theory of Scaling Laws for In-Context Regression: Depth, Width, Context and Time","created":"2025-10-01","cited_by_count":16,"area":null},{"id":"2505.01996","title":"Always Skip Attention","created":"2025-05-04","cited_by_count":13,"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":"2405.15926","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers","created":"2024-05-24","cited_by_count":9,"area":null},{"id":"2505.12455","title":"AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections","created":"2025-05-18","cited_by_count":9,"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":"2310.02012","title":"Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion","created":"2023-10-03","cited_by_count":8,"area":null},{"id":"2601.21942","title":"Clustering in Deep Stochastic Transformers","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2402.15415","title":"Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2405.16630","title":"Bayesian Inference with Deep Weakly Nonlinear Networks","created":"2024-05-26","cited_by_count":5,"area":null},{"id":"2506.00846","title":"Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2506.03790","title":"Attention-Only Transformers via Unrolled Subspace Denoising","created":"2025-06-04","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":"2410.08024","title":"Pretraining Graph Transformers with Atom-in-a-Molecule Quantum Properties for Improved ADMET Modeling","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2410.09637","title":"ReLU's Revival: On the Entropic Overload in Normalization-Free Large Language Models","created":"2024-10-12","cited_by_count":3,"area":null},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2505.13112","title":"Attention-based clustering","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2506.01582","title":"Bayes optimal learning of attention-indexed models","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2410.15578","title":"Generalized Probabilistic Attention Mechanism in Transformers","created":"2024-10-21","cited_by_count":2,"area":null},{"id":"2510.09210","title":"Provable Watermarking for Data Poisoning Attacks","created":"2025-10-10","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":"2406.09877","title":"Federated Learning with Flexible Architectures","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2601.16514","title":"Finite-Time Analysis of Gradient Descent for Shallow Transformers","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2605.06599","title":"Weight-Decay Turns Transformer Loss Landscapes Villani: Functional-Analytic Foundations for Optimization and Generalization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.30860","title":"Bayesian Inference with Shaped Deep Non-linear MLPs","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2407.06765","title":"A Generalization Bound for Nearly-Linear Networks","created":"2024-07-09","cited_by_count":0,"area":null},{"id":"2411.14789","title":"Simplifying CLIP: Unleashing the Power of Large-Scale Models on Consumer-level Computers","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2503.23982","title":"Deep Neural Nets as Hamiltonians","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2605.14370","title":"Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel","created":"2026-05-14","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":"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}