{"total":57,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380,"area":null},{"id":"2204.00595","title":"Monarch: Expressive Structured Matrices for Efficient and Accurate Training","created":"2022-04-01","cited_by_count":106,"area":null},{"id":"2406.02214","title":"SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining","created":"2024-06-04","cited_by_count":45,"area":null},{"id":"2310.09528","title":"Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks","created":"2023-10-14","cited_by_count":44,"area":null},{"id":"2205.13571","title":"Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations","created":"2022-05-26","cited_by_count":43,"area":null},{"id":"2111.14655","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2209.13569","title":"Exploring Low Rank Training of Deep Neural Networks","created":"2022-09-27","cited_by_count":30,"area":null},{"id":"2502.10940","title":"CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation","created":"2025-02-16","cited_by_count":28,"area":null},{"id":"2309.03160","title":"ResFields: Residual Neural Fields for Spatiotemporal Signals","created":"2023-09-06","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":"2305.02538","title":"Cuttlefish: Low-Rank Model Training without All the Tuning","created":"2023-05-04","cited_by_count":25,"area":null},{"id":"2411.19146","title":"Puzzle: Distillation-Based NAS for Inference-Optimized LLMs","created":"2024-11-28","cited_by_count":17,"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":"2402.14646","title":"CoLoRA: Continuous low-rank adaptation for reduced implicit neural modeling of parameterized partial differential equations","created":"2024-02-22","cited_by_count":14,"area":null},{"id":"2208.13141","title":"Federated Learning of Large Models at the Edge via Principal Sub-Model Training","created":"2022-08-28","cited_by_count":13,"area":null},{"id":"2306.01485","title":"Robust low-rank training via approximate orthonormal constraints","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2305.19059","title":"Geometry-aware training of factorized layers in tensor Tucker format","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2504.12883","title":"Mirror, Mirror of the Flow: How Does Regularization Shape Implicit Bias?","created":"2025-04-17","cited_by_count":12,"area":null},{"id":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2402.03991","title":"Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks","created":"2024-02-06","cited_by_count":11,"area":null},{"id":"2508.02668","title":"LOST: Low-rank and Sparse Pre-training for Large Language Models","created":"2025-08-04","cited_by_count":10,"area":null},{"id":"2303.11525","title":"Sparse-IFT: Sparse Iso-FLOP Transformations for Maximizing Training Efficiency","created":"2023-03-21","cited_by_count":8,"area":null},{"id":"2305.15598","title":"ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2406.17887","title":"Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees","created":"2024-06-25","cited_by_count":7,"area":null},{"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":"2407.09835","title":"Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis","created":"2024-07-13","cited_by_count":6,"area":null},{"id":"2602.12429","title":"Stabilizing Native Low-Rank LLM Pretraining","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2410.18720","title":"GeoLoRA: Geometric integration for parameter efficient fine-tuning","created":"2024-10-24","cited_by_count":5,"area":null},{"id":"2506.17475","title":"A geometric framework for momentum-based optimizers for low-rank training","created":"2025-06-20","cited_by_count":5,"area":null},{"id":"2406.03768","title":"Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective","created":"2024-06-06","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":"2606.12921","title":"LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold","created":"2026-06-11","cited_by_count":4,"area":null},{"id":"2202.00834","title":"Nonlinear Initialization Methods for Low-Rank Neural Networks","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2311.05061","title":"Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics","created":"2023-11-08","cited_by_count":3,"area":null},{"id":"2405.03089","title":"Structure-Preserving Network Compression Via Low-Rank Induced Training Through Linear Layers Composition","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2410.07771","title":"Full-Rank No More: Low-Rank Weight Training for Modern Speech Recognition Models","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2406.16450","title":"Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2512.12131","title":"BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models","created":"2025-12-13","cited_by_count":2,"area":null},{"id":"2410.03497","title":"Collaborative and Efficient Personalization with Mixtures of Adaptors","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2507.09428","title":"On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization","created":"2025-07-12","cited_by_count":1,"area":null},{"id":"2511.04485","title":"Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2602.06476","title":"Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2606.28932","title":"DLR: Zero-Inference-Cost Latent Residuals for Low-Rank Pre-Training","created":"2026-06-27","cited_by_count":1,"area":null},{"id":"2607.08754","title":"SLORR: Simple and Efficient In-Training Low-Rank Regularization","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2210.04807","title":"Efficient NTK using Dimensionality Reduction","created":"2022-10-10","cited_by_count":0,"area":null},{"id":"2211.11242","title":"L-MAE: Masked Autoencoders are Semantic Segmentation Datasets Augmenter","created":"2022-11-21","cited_by_count":0,"area":null},{"id":"2308.13300","title":"Learning Compact Neural Networks with Deep Overparameterised Multitask Learning","created":"2023-08-25","cited_by_count":0,"area":null},{"id":"2403.00606","title":"Flattening Singular Values of Factorized Convolution for Medical Images","created":"2024-03-01","cited_by_count":0,"area":null},{"id":"2406.08904","title":"AdaPTwin: Low-Cost Adaptive Compression of Product Twins in Transformers","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2410.24106","title":"On Sampling Strategies for Spectral Model Sharding","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2510.01718","title":"Accelerating Attention with Basis Decomposition","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2605.03667","title":"ELAS: Efficient Pre-Training of Low-Rank Large Language Models via 2:4 Activation Sparsity","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.28573","title":"Efficient Pre-Training of LLMs through Truncated SVD Representations","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2609.21039","title":"Stiefel-AdamW: Geometry-Aware AdamW for Linear Factorization Blocks","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21126","title":"Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.32615","title":"Stabilizing the Dynamic Low-Rank Training","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}