{"total":75,"rows":[{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758,"area":null},{"id":"2403.03507","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","created":"2024-03-06","cited_by_count":463,"area":null},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"area":null},{"id":"2406.15765","title":"Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration","created":"2024-06-22","cited_by_count":74,"area":null},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"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":"2410.01623","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2407.08296","title":"Q-GaLore: Quantized GaLore with INT4 Projection and Layer-Adaptive Low-Rank Gradients","created":"2024-07-11","cited_by_count":38,"area":null},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37,"area":null},{"id":"2405.00361","title":"AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts","created":"2024-05-01","cited_by_count":34,"area":null},{"id":"2404.02827","title":"BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models","created":"2024-04-03","cited_by_count":27,"area":null},{"id":"2407.11239","title":"From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications","created":"2024-07-15","cited_by_count":25,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2402.17263","title":"MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning","created":"2024-02-27","cited_by_count":19,"area":null},{"id":"2405.17991","title":"VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections","created":"2024-05-28","cited_by_count":18,"area":null},{"id":"2406.17660","title":"Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients","created":"2024-06-25","cited_by_count":18,"area":null},{"id":"2502.01586","title":"SubTrack++ : Gradient Subspace Tracking for Scalable LLM Training","created":"2025-02-03","cited_by_count":16,"area":null},{"id":"2410.18965","title":"On the Crucial Role of Initialization for Matrix Factorization","created":"2024-10-24","cited_by_count":15,"area":null},{"id":"2409.10927","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2410.08305","title":"Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation","created":"2024-10-10","cited_by_count":13,"area":null},{"id":"2407.19580","title":"Mini-batch Coresets for Memory-efficient Language Model Training on Data Mixtures","created":"2024-07-28","cited_by_count":12,"area":null},{"id":"2412.19616","title":"Gradient Weight-normalized Low-rank Projection for Efficient LLM Training","created":"2024-12-27","cited_by_count":11,"area":null},{"id":"2507.02503","title":"Continual Gradient Low-Rank Projection Fine-Tuning for LLMs","created":"2025-07-03","cited_by_count":11,"area":null},{"id":"2410.08598","title":"Parameter-Efficient Fine-Tuning of Large Language Models using Semantic Knowledge Tuning","created":"2024-10-11","cited_by_count":10,"area":null},{"id":"2410.14802","title":"Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems","created":"2024-10-18","cited_by_count":10,"area":null},{"id":"2503.18225","title":"DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation","created":"2025-03-23","cited_by_count":10,"area":null},{"id":"2505.11816","title":"Continuous Subspace Optimization for Continual Learning","created":"2025-05-17","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":"2405.18380","title":"Outlier-weighed Layerwise Sampling for LLM Fine-tuning","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2412.00071","title":"COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection","created":"2024-11-26","cited_by_count":8,"area":null},{"id":"2502.05790","title":"Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining","created":"2025-02-09","cited_by_count":7,"area":null},{"id":"2507.06558","title":"The Primacy of Magnitude in Low-Rank Adaptation","created":"2025-07-09","cited_by_count":7,"area":null},{"id":"2509.18993","title":"CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure","created":"2025-09-23","cited_by_count":7,"area":null},{"id":"2409.12371","title":"Communication-Efficient Federated Low-Rank Update Algorithm and its Connection to Implicit Regularization","created":"2024-09-19","cited_by_count":6,"area":null},{"id":"2407.01491","title":"Expressive and Generalizable Low-rank Adaptation for Large Models via Slow Cascaded Learning","created":"2024-07-01","cited_by_count":5,"area":null},{"id":"2412.13860","title":"Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepali","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2405.15481","title":"Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2412.18729","title":"Optimizing Large Language Models with an Enhanced LoRA Fine-Tuning Algorithm for Efficiency and Robustness in NLP Tasks","created":"2024-12-25","cited_by_count":4,"area":null},{"id":"2509.05213","title":"An Efficient Subspace Algorithm for Federated Learning on Heterogeneous Data","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2505.22602","title":"One Rank at a Time: Cascading Error Dynamics in Sequential Learning","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2507.00327","title":"Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes","created":"2025-06-30","cited_by_count":3,"area":null},{"id":"2604.21905","title":"Low-Rank Adaptation Redux for Large Models","created":"2026-04-23","cited_by_count":3,"area":null},{"id":"2404.02507","title":"Lifelong Event Detection with Embedding Space Separation and Compaction","created":"2024-04-03","cited_by_count":2,"area":null},{"id":"2406.06564","title":"SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2407.01649","title":"FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2407.11186","title":"Empowering Persian LLMs for Instruction Following: A Novel Dataset and Training Approach","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2409.00590","title":"COMOGen: A Controllable Text-to-3D Multi-object Generation Framework","created":"2024-09-01","cited_by_count":2,"area":null},{"id":"2504.03718","title":"Task-Aware Parameter-Efficient Fine-Tuning of Large Pre-Trained Models at the Edge","created":"2025-03-29","cited_by_count":2,"area":null},{"id":"2601.07507","title":"High-Rank Structured Modulation for Parameter-Efficient Fine-Tuning","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2601.22708","title":"A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2605.21147","title":"SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2501.07237","title":"GWT: Scalable Optimizer State Compression for Large Language Model Training","created":"2025-01-13","cited_by_count":1,"area":null},{"id":"2502.07739","title":"HRP: High-Rank Preheating for Superior LoRA Initialization","created":"2025-02-11","cited_by_count":1,"area":null},{"id":"2502.13811","title":"On the Duality between Gradient Transformations and Adapters","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2505.17872","title":"Mixture of Low Rank Adaptation with Partial Parameter Sharing for Time Series Forecasting","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.01897","title":"MLorc: Momentum Low-rank Compression for Memory Efficient Large Language Model Adaptation","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2506.02882","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2510.01878","title":"Geometrically Principled Randomized Optimization for Efficient LLM Training","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2512.07112","title":"FOAM: Blocked State Folding for Memory-Efficient LLM Training","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.15764","title":"AdaGradSelect: An adaptive gradient-guided layer selection method for efficient fine-tuning of SLMs","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2604.07808","title":"GRASS: Gradient-based Adaptive Layer-wise Importance Sampling for Memory-efficient Large Language Model Fine-tuning","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.09406","title":"OASIS: Online Activation Subspace Learning for Memory-Efficient Training","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.05659","title":"Structural Correspondence and Universal Approximation in Diagonal plus Low-Rank Neural Networks","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.13767","title":"Beyond LoRA: Is Sparsity-Induced Adaptation Better?","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2409.09549","title":"COMFORT: A Continual Fine-Tuning Framework for Foundation Models Targeted at Consumer Healthcare","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2604.27308","title":"BoostLoRA: Growing Effective Rank by Boosting Adapters","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.21177","title":"ChunkFT: Byte-Streamed Optimization for Memory-Efficient Full Fine-Tuning","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.03209","title":"DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.12883","title":"The Hidden Power of Scaling Factor in LoRA Optimization","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2608.03579","title":"Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.06563","title":"Theoretical Foundations of Communication-Efficient, Robust, and Practical Distributed and Federated Optimization","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.26430","title":"Fine-Tuning of Transformer models with Frames","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2610.19700","title":"ReGRA: Residual-Gradient Adaptation for Complementary Low-Rank Fine-Tuning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}