{"total":67,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380,"area":null},{"id":"2206.15144","title":"Neural Networks can Learn Representations with Gradient Descent","created":"2022-06-30","cited_by_count":161,"area":null},{"id":"2202.14026","title":"Robust Training under Label Noise by Over-parameterization","created":"2022-02-28","cited_by_count":93,"area":null},{"id":"2201.12498","title":"Investigating Why Contrastive Learning Benefits Robustness Against Label Noise","created":"2022-01-29","cited_by_count":46,"area":null},{"id":"2501.13787","title":"Parameter-Efficient Fine-Tuning for Foundation Models","created":"2025-01-23","cited_by_count":45,"area":null},{"id":"2110.02424","title":"Spectral Bias in Practice: The Role of Function Frequency in Generalization","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2211.06506","title":"Spectral Evolution and Invariance in Linear-width Neural Networks","created":"2022-11-11","cited_by_count":30,"area":null},{"id":"2205.11005","title":"Parameter-Efficient Sparsity for Large Language Models Fine-Tuning","created":"2022-05-23","cited_by_count":27,"area":null},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27,"area":null},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2211.07844","title":"Characterizing the Spectrum of the NTK via a Power Series Expansion","created":"2022-11-15","cited_by_count":22,"area":null},{"id":"2110.12425","title":"Kernelized Heterogeneous Risk Minimization","created":"2021-10-24","cited_by_count":21,"area":null},{"id":"2201.06142","title":"Towards Sample-efficient Overparameterized Meta-learning","created":"2022-01-16","cited_by_count":21,"area":null},{"id":"2302.09235","title":"Generalization and Stability of Interpolating Neural Networks with Minimal Width","created":"2023-02-18","cited_by_count":21,"area":null},{"id":"2110.11749","title":"Feature Learning and Signal Propagation in Deep Neural Networks","created":"2021-10-22","cited_by_count":18,"area":null},{"id":"2502.00896","title":"LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation","created":"2025-02-02","cited_by_count":17,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2405.03251","title":"Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond","created":"2024-05-06","cited_by_count":15,"area":"diffusion"},{"id":"2104.05605","title":"Understanding Overparameterization in Generative Adversarial Networks","created":"2021-04-12","cited_by_count":14,"area":null},{"id":"2104.14132","title":"Generalization Guarantees for Neural Architecture Search with Train-Validation Split","created":"2021-04-29","cited_by_count":14,"area":null},{"id":"2310.12408","title":"Provable Guarantees for Neural Networks via Gradient Feature Learning","created":"2023-10-19","cited_by_count":14,"area":null},{"id":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14,"area":null},{"id":"2311.04163","title":"Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization","created":"2023-11-07","cited_by_count":13,"area":null},{"id":"2105.02468","title":"Relative stability toward diffeomorphisms indicates performance in deep nets","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2206.02927","title":"Spectral Bias Outside the Training Set for Deep Networks in the Kernel Regime","created":"2022-06-06","cited_by_count":11,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2102.10734","title":"Provable Super-Convergence with a Large Cyclical Learning Rate","created":"2021-02-22","cited_by_count":10,"area":null},{"id":"2107.09437","title":"Edge of chaos as a guiding principle for modern neural network training","created":"2021-07-20","cited_by_count":10,"area":null},{"id":"2406.12629","title":"SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation","created":"2024-06-18","cited_by_count":10,"area":null},{"id":"2512.18248","title":"On the Convergence Rate of LoRA Gradient Descent","created":"2025-12-20","cited_by_count":10,"area":null},{"id":"2201.04738","title":"Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks","created":"2022-01-12","cited_by_count":9,"area":null},{"id":"2111.00160","title":"DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models","created":"2021-10-30","cited_by_count":8,"area":null},{"id":"2403.06869","title":"Impact of Noisy Supervision in Foundation Model Learning","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2412.16748","title":"Solving Inverse Problems via Diffusion Optimal Control","created":"2024-12-21","cited_by_count":8,"area":null},{"id":"2602.06801","title":"On the Non-Identifiability of Steering Vectors in Large Language Models","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2106.11486","title":"Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification","created":"2021-06-22","cited_by_count":7,"area":null},{"id":"2107.14324","title":"Deep Networks Provably Classify Data on Curves","created":"2021-07-29","cited_by_count":6,"area":null},{"id":"2112.07806","title":"Representation Alignment in Neural Networks","created":"2021-12-15","cited_by_count":6,"area":null},{"id":"2404.09326","title":"Weight Copy and Low-Rank Adaptation for Few-Shot Distillation of Vision Transformers","created":"2024-04-14","cited_by_count":6,"area":"distill"},{"id":"2407.01320","title":"Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning","created":"2024-07-01","cited_by_count":6,"area":null},{"id":"2106.06153","title":"Towards Understanding Generalization via Decomposing Excess Risk Dynamics","created":"2021-06-11","cited_by_count":5,"area":null},{"id":"2406.17740","title":"Structured Unrestricted-Rank Matrices for Parameter Efficient Fine-tuning","created":"2024-06-25","cited_by_count":5,"area":null},{"id":"2501.00339","title":"GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compression","created":"2024-12-31","cited_by_count":5,"area":null},{"id":"2602.15823","title":"CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing","created":"2026-02-17","cited_by_count":5,"area":"alignment"},{"id":"2210.08363","title":"Data-Efficient Augmentation for Training Neural Networks","created":"2022-10-15","cited_by_count":4,"area":null},{"id":"2407.04797","title":"Revealing the Utilized Rank of Subspaces of Learning in Neural Networks","created":"2024-07-05","cited_by_count":4,"area":null},{"id":"2602.11137","title":"Weight Decay Improves Language Model Plasticity","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2110.02333","title":"On the Impact of Stable Ranks in Deep Nets","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2305.14521","title":"Few-shot Adaptation to Distribution Shifts By Mixing Source and Target Embeddings","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2405.07527","title":"Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models","created":"2024-05-13","cited_by_count":3,"area":null},{"id":"2501.18596","title":"DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2606.17667","title":"Handling Feature Heterogeneity with Learnable Graph Patches","created":"2026-06-16","cited_by_count":3,"area":null},{"id":"2405.20278","title":"Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2510.24299","title":"Verifying Large Language Models' Reasoning Paths via Correlation Matrix Rank","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2211.14960","title":"Label Alignment Regularization for Distribution Shift","created":"2022-11-27","cited_by_count":1,"area":null},{"id":"2404.01084","title":"AILS-NTUA at SemEval-2024 Task 9: Cracking Brain Teasers: Transformer Models for Lateral Thinking Puzzles","created":"2024-04-01","cited_by_count":1,"area":"lr"},{"id":"2602.12384","title":"Why Deep Jacobian Spectra Separate: Depth-Induced Scaling and Singular-Vector Alignment","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2603.16569","title":"Deep Tabular Representation Corrector","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2603.29824","title":"Curvature-Guided LoRA: Matching Full Fine-Tuning in Function Space","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2310.03833","title":"Learning A Disentangling Representation For PU Learning","created":"2023-10-05","cited_by_count":0,"area":null},{"id":"2310.17378","title":"Optimization dependent generalization bound for ReLU networks based on sensitivity in the tangent bundle","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2412.18756","title":"Towards a Statistical Understanding of Neural Networks: Beyond the Neural Tangent Kernel Theories","created":"2024-12-25","cited_by_count":0,"area":null},{"id":"2507.11183","title":"Quantized Rank Reduction: A Communications-Efficient Federated Learning Scheme for Network-Critical Applications","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.20049","title":"Projective Kolmogorov Arnold Neural Networks (P-KANs): Entropy-Driven Functional Space Discovery for Interpretable Machine Learning","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2512.23109","title":"How Much Data Is Enough? Uniform Convergence Bounds for Generative & Vision-Language Models under Low-Dimensional Structure","created":"2025-12-28","cited_by_count":0,"area":"mllm"},{"id":"2608.24210","title":"A Data-dependent Early Stopping Rule using Rademacher Complexity with L1-norm","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2610.09919","title":"Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its Breaking","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}