{"total":94,"rows":[{"id":"2502.04959","title":"No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces","created":"2025-02-07","cited_by_count":96,"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":"2505.18738","title":"AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping","created":"2025-05-24","cited_by_count":23,"area":null},{"id":"2510.13003","title":"OPLoRA: Orthogonal Projection LoRA Prevents Catastrophic Forgetting during Parameter-Efficient Fine-Tuning","created":"2025-10-14","cited_by_count":21,"area":null},{"id":"2410.07170","title":"Parameter Efficient Fine-tuning via Explained Variance Adaptation","created":"2024-10-09","cited_by_count":20,"area":null},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2504.07097","title":"Sculpting Subspaces: Constrained Full Fine-Tuning in LLMs for Continual Learning","created":"2025-04-09","cited_by_count":15,"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":"2503.06982","title":"Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2503.16322","title":"Ultra-Resolution Adaptation with Ease","created":"2025-03-20","cited_by_count":13,"area":"diffusion"},{"id":"2507.12142","title":"LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters","created":"2025-07-16","cited_by_count":13,"area":null},{"id":"2412.05723","title":"Training-Free Bayesianization for Low-Rank Adapters of Large Language Models","created":"2024-12-07","cited_by_count":12,"area":null},{"id":"2502.12171","title":"GoRA: Gradient-driven Adaptive Low Rank Adaptation","created":"2025-02-13","cited_by_count":12,"area":null},{"id":"2506.00772","title":"LIFT the Veil for the Truth: Principal Weights Emerge after Rank Reduction for Reasoning-Focused Supervised Fine-Tuning","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2512.23165","title":"Evaluating Parameter Efficient Methods for RLVR","created":"2025-12-29","cited_by_count":12,"area":null},{"id":"2602.17155","title":"Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization","created":"2026-02-19","cited_by_count":12,"area":null},{"id":"2508.04117","title":"Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks","created":"2025-08-06","cited_by_count":11,"area":"lr"},{"id":"2407.09946","title":"Low-Rank Interconnected Adaptation across Layers","created":"2024-07-13","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":"2508.00230","title":"Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product","created":"2025-08-01","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":"2410.16801","title":"Controlled Low-Rank Adaptation with Subspace Regularization for Continued Training on Large Language Models","created":"2024-10-22","cited_by_count":9,"area":null},{"id":"2502.15828","title":"A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models","created":"2025-02-20","cited_by_count":9,"area":"moe"},{"id":"2410.01870","title":"PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers","created":"2024-10-02","cited_by_count":8,"area":null},{"id":"2412.06071","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","created":"2024-12-08","cited_by_count":8,"area":null},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","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":"2409.16722","title":"PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2504.00851","title":"Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations","created":"2025-04-01","cited_by_count":5,"area":null},{"id":"2505.23099","title":"Weight Spectra Induced Efficient Model Adaptation","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2507.07580","title":"COALA: Numerically Stable and Efficient Framework for Context-Aware Low-Rank Approximation","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2409.01035","title":"Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning","created":"2024-09-02","cited_by_count":4,"area":null},{"id":"2506.02724","title":"WeightLoRA: Keep Only Necessary Adapters","created":"2025-06-03","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":"2510.24561","title":"LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2602.09492","title":"Beware of the Batch Size: Hyperparameter Bias in Evaluating LoRA","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2412.20891","title":"DoTA: Weight-Decomposed Tensor Adaptation for Large Language Models","created":"2024-12-30","cited_by_count":3,"area":null},{"id":"2603.08014","title":"FedMomentum: Preserving LoRA Training Momentum in Federated Fine-Tuning","created":"2026-03-09","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":"2605.10973","title":"Rotation-Preserving Supervised Fine-Tuning","created":"2026-05-08","cited_by_count":3,"area":null},{"id":"2502.19747","title":"HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2506.03230","title":"DiaBlo: Diagonal Blocks Are Sufficient For Finetuning","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2508.01961","title":"Kron-LoRA: Hybrid Kronecker-LoRA Adapters for Scalable, Sustainable Fine-tuning","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","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":"2602.03493","title":"Least but not Last: Fine-tuning Intermediate Principal Components for Better Performance-Forgetting Trade-Offs","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.14382","title":"StAR: Segment Anything Reasoner","created":"2026-03-15","cited_by_count":2,"area":null},{"id":"2605.01046","title":"Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2605.06175","title":"VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts","created":"2026-05-07","cited_by_count":2,"area":"vla"},{"id":"2607.04118","title":"Parametric Memory Decoding for Zero-Shot Routing in LoRA-Based External Parametric Memory","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.23711","title":"The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2505.23094","title":"MAP: Revisiting Weight Decomposition for Low-Rank Adaptation","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2508.00873","title":"FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA","created":"2025-07-21","cited_by_count":1,"area":null},{"id":"2510.21175","title":"Memory-Free Continual Learning with Null Space Adaptation for Zero-Shot Vision-Language Models","created":"2025-10-24","cited_by_count":1,"area":"mllm"},{"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":"2603.08445","title":"Alfa: Attentive Low-Rank Filter Adaptation for Structure-Aware Cross-Domain Personalized Gaze Estimation","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2604.01310","title":"Sparse Spectral LoRA: Routed Experts for Medical VLMs","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2605.25565","title":"RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism","created":"2026-05-25","cited_by_count":1,"area":"moe"},{"id":"2606.06494","title":"TailLoR: Protecting Principal Components in Parameter-Efficient Continual Learning","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2607.02576","title":"CORA: Per-Slice Coherent Orthogonal Rotation for SVD-based Low-Rank Adaptation","created":"2026-06-30","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":"2508.19353","title":"Efficient Multi-Source Knowledge Transfer by Model Merging","created":"2025-08-26","cited_by_count":0,"area":null},{"id":"2509.00046","title":"Exploring and Reshaping the Weight Distribution in LLM","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2510.08034","title":"AILoRA: Function-Aware Asymmetric Initialization for Low-Rank Adaptation of Large Language Models","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2512.23485","title":"FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2603.07926","title":"IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.01762","title":"FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models","created":"2026-04-02","cited_by_count":0,"area":"moe"},{"id":"2604.18075","title":"Enhancing Continual Learning of Vision-Language Models via Dynamic Prefix Weighting","created":"2026-04-20","cited_by_count":0,"area":"mllm"},{"id":"2605.06166","title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","created":"2026-05-07","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":"2605.12752","title":"Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning","created":"2026-05-12","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":"2605.22869","title":"FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.24549","title":"PALoRA: Projection-Adaptive LoRA for Preserving Reasoning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2606.00132","title":"Foundation-Preserving Optimization in Generalized Eigenspace","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.31092","title":"Fora: From Weight-Space to Function-Space Protection in Capability-Preserving Fine-Tuning","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2606.31813","title":"Geometry-Preserving Orthonormal Initialization for Low-Rank Adaptation in RLVR","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.04306","title":"SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation","created":"2026-07-05","cited_by_count":0,"area":"distill"},{"id":"2607.22489","title":"\\k{appa}-LoRA: Condition Numbers Reveal Which LoRA Matrices Worth Updating","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.05253","title":"Beyond Rotations: AuroOFT for Expressive Quantized Orthogonal Fine-Tuning","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.26155","title":"VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation","created":"2026-07-04","cited_by_count":0,"area":"mllm"},{"id":"2608.31036","title":"Normalized Low-Rank Adaptation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01374","title":"Behaviorally Effective LoRA Writes Are Sparse and Structured","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.02006","title":"Train What You Deploy: Closing the MLP Reachability Gap in Low-Rank Clone Distillation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.04715","title":"PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05885","title":"One Rate Is Not Enough: Adaptive Anisotropic Learning Rates for LoRA Fine-Tuning","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.19985","title":"Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.25618","title":"Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"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":"2610.06621","title":"Frozen Factor or Spectral Band? Disentangling Two Choices in Low-Rank LoRA","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.17730","title":"DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18634","title":"Geometric Calibration of Supervised Fine-Tuning","created":"2026-10-13","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}