{"total":76,"rows":[{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67,"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":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"area":null},{"id":"2502.00987","title":"RandLoRA: Full-rank parameter-efficient fine-tuning of large models","created":"2025-02-03","cited_by_count":35,"area":null},{"id":"2411.19557","title":"Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning","created":"2024-11-29","cited_by_count":22,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"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":"2505.21289","title":"LoFT: Low-Rank Adaptation That Behaves Like Full Fine-Tuning","created":"2025-05-27","cited_by_count":14,"area":null},{"id":"2510.01938","title":"StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold","created":"2025-10-02","cited_by_count":14,"area":null},{"id":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2408.10280","title":"NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models","created":"2024-08-18","cited_by_count":13,"area":null},{"id":"2501.16559","title":"LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation","created":"2025-01-27","cited_by_count":11,"area":"diffusion"},{"id":"2408.14572","title":"CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation","created":"2024-08-26","cited_by_count":10,"area":null},{"id":"2502.15436","title":"Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning","created":"2025-02-21","cited_by_count":10,"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":"2602.04998","title":"Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning","created":"2026-02-04","cited_by_count":10,"area":null},{"id":"2506.05568","title":"Ravan: Multi-Head Low-Rank Adaptation for Federated Fine-Tuning","created":"2025-06-05","cited_by_count":9,"area":null},{"id":"2410.10075","title":"RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2509.25622","title":"Layer-wise dynamic rank for compressing large language models","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2412.08587","title":"Advancing Single and Multi-task Text Classification through Large Language Model Fine-tuning","created":"2024-12-11","cited_by_count":7,"area":null},{"id":"2505.12532","title":"Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision","created":"2025-05-18","cited_by_count":7,"area":null},{"id":"2506.00799","title":"Uni-LoRA: One Vector is All You Need","created":"2025-06-01","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":"2510.23123","title":"Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation","created":"2025-10-27","cited_by_count":6,"area":null},{"id":"2409.16722","title":"PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2502.12122","title":"Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRA","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2505.11235","title":"Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2506.13187","title":"Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2501.12067","title":"EDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition","created":"2025-01-21","cited_by_count":3,"area":null},{"id":"2505.14238","title":"ABBA-Adapters: Efficient and Expressive Fine-Tuning of Foundation Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2506.18923","title":"Mix-of-Language-Experts Architecture for Multilingual Programming","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2509.17688","title":"TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2506.01049","title":"Taming LLMs by Scaling Learning Rates with Gradient Grouping","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2506.16787","title":"Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps","created":"2025-06-20","cited_by_count":2,"area":null},{"id":"2507.08044","title":"ConsNoTrainLoRA: Data-driven Weight Initialization of Low-rank Adapters using Constraints","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2510.08513","title":"SliceFine: The Universal Winning-Slice Hypothesis for Pretrained Networks","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2602.09169","title":"Train Less, Infer Faster: Efficient Model Finetuning and Compression via Structured Sparsity","created":"2026-02-09","cited_by_count":2,"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":"2505.14367","title":"Dual Decomposition of Weights and Singular Value Low Rank Adaptation","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2506.24092","title":"WaRA: Wavelet Low-Rank Adaptation for Medical Image Classification","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2508.21810","title":"QR-LoRA: QR-Based Low-Rank Adaptation for Efficient Fine-Tuning of Large Language Models","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2602.01008","title":"Adapting Where It Matters: Depth-Aware Adaptation for Efficient Multilingual Speech Recognition in Low-Resource Languages","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2602.10993","title":"LoRA-Squeeze: Simple and Effective Post-Tuning and In-Tuning Compression of LoRA Modules","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2602.17510","title":"LORA-CRAFT: Cross-layer Rank Adaptation via Frozen Tucker Decomposition of Pre-trained Attention Weights","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2607.03065","title":"Spectral Rewiring for Exploration, Purification, and Model Merging","created":"2026-07-03","cited_by_count":1,"area":"lr"},{"id":"2607.14506","title":"Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards","created":"2026-07-16","cited_by_count":1,"area":"lr"},{"id":"2608.01624","title":"Not the Dimension, the Norm: What Matters in Gradient-Free Weight Perturbation of Language Models","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.12332","title":"Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation?","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2609.00762","title":"Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2501.19050","title":"Norm-Bounded Low-Rank Adaptation","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2502.06970","title":"Model Diffusion for Certifiable Few-shot Transfer Learning","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2502.10620","title":"ProMRVL-CAD: Proactive Dialogue System with Multi-Round Vision-Language Interactions for Computer-Aided Diagnosis","created":"2025-02-15","cited_by_count":0,"area":null},{"id":"2506.12394","title":"LARGO: Low-Rank Regulated Gradient Projection for Robust Parameter Efficient Fine-Tuning","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2507.01841","title":"Automatic Rank Determination for Low-Rank Adaptation via Submodular Function Maximization","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2508.19353","title":"Efficient Multi-Source Knowledge Transfer by Model Merging","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2511.00101","title":"Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2602.07479","title":"ODELoRA: Training Low-Rank Adaptation by Solving Ordinary Differential Equations","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2604.21901","title":"GiVA: Gradient-Informed Bases for Vector-Based Adaptation","created":"2026-04-23","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":"2605.07706","title":"Bayesian Fine-tuning in Projected Subspaces","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.08174","title":"CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.11872","title":"LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.12207","title":"Not How Many, But Which: Parameter Placement in Low-Rank Adaptation","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.14217","title":"PreFT: Prefill-only finetuning for efficient inference","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15916","title":"LoCO: Low-rank Compositional Rotation Fine-tuning","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2607.11940","title":"CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2607.23837","title":"Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.21172","title":"Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.13654","title":"Multimodal Foundation Models Adaptation based on Domain-Aware Relaxed Orthogonal Subspace for Remote Sensing","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.29800","title":"Adaptive Fisher-Whitened Cross-Covariance for Low-Resource Speech Recognition","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.32792","title":"Understanding and Exploiting Anisotropy in Post-Training","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02067","title":"Learn the Directions, Normalize the Gains: Post-Training Normalization for LoRA","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05800","title":"Adaptive Utilization of Low-Rank Adaptation via Conditioned Gating","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.06621","title":"Frozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}