{"total":300,"rows":[{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656,"area":null},{"id":"2402.12354","title":"LoRA+: Efficient Low Rank Adaptation of Large Models","created":"2024-02-19","cited_by_count":377,"area":null},{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197,"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":"2406.09044","title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning","created":"2024-06-13","cited_by_count":94,"area":null},{"id":"2405.17604","title":"LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters","created":"2024-05-27","cited_by_count":76,"area":null},{"id":"2311.09578","title":"Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying","created":"2023-11-16","cited_by_count":65,"area":null},{"id":"2406.01563","title":"LoFiT: Localized Fine-tuning on LLM Representations","created":"2024-06-03","cited_by_count":57,"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":"2502.18461","title":"K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs","created":"2025-02-25","cited_by_count":48,"area":null},{"id":"2406.11909","title":"Mixture-of-Subspaces in Low-Rank Adaptation","created":"2024-06-16","cited_by_count":47,"area":"diffusion"},{"id":"2501.01765","title":"SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation","created":"2025-01-03","cited_by_count":42,"area":"safety"},{"id":"2402.07721","title":"LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation","created":"2024-02-12","cited_by_count":38,"area":null},{"id":"2402.15179","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","created":"2024-02-23","cited_by_count":37,"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":"2403.16187","title":"ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models","created":"2024-03-24","cited_by_count":36,"area":null},{"id":"2408.06621","title":"Towards Robust and Parameter-Efficient Knowledge Unlearning for LLMs","created":"2024-08-13","cited_by_count":36,"area":"lr"},{"id":"2405.12130","title":"MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning","created":"2024-05-20","cited_by_count":31,"area":null},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2505.02795","title":"HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2025-05-05","cited_by_count":31,"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":"2410.14425","title":"Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillation","created":"2024-10-18","cited_by_count":27,"area":"safety"},{"id":"2406.04112","title":"Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2408.04638","title":"Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective","created":"2024-07-30","cited_by_count":25,"area":null},{"id":"2407.00066","title":"Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead","created":"2024-06-17","cited_by_count":24,"area":null},{"id":"2512.05117","title":"The Universal Weight Subspace Hypothesis","created":"2025-12-04","cited_by_count":24,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"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":"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":"2410.18035","title":"MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning","created":"2024-10-23","cited_by_count":19,"area":"moe"},{"id":"2504.07448","title":"LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation","created":"2025-04-10","cited_by_count":19,"area":null},{"id":"2311.13171","title":"ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization","created":"2023-11-22","cited_by_count":18,"area":null},{"id":"2410.11305","title":"QSpec: Speculative Decoding with Complementary Quantization Schemes","created":"2024-10-15","cited_by_count":18,"area":"inference"},{"id":"2406.13175","title":"Sparse High Rank Adapters","created":"2024-06-19","cited_by_count":17,"area":null},{"id":"2504.21099","title":"A Survey on Parameter-Efficient Fine-Tuning for Foundation Models in Federated Learning","created":"2025-04-29","cited_by_count":17,"area":null},{"id":"2402.16902","title":"PRoLoRA: Partial Rotation Empowers More Parameter-Efficient LoRA","created":"2024-02-24","cited_by_count":16,"area":null},{"id":"2406.12832","title":"LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation","created":"2024-06-18","cited_by_count":16,"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":"2405.17484","title":"Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation","created":"2024-05-24","cited_by_count":15,"area":null},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2312.17522","title":"Overview of the PromptCBLUE Shared Task in CHIP2023","created":"2023-12-29","cited_by_count":14,"area":null},{"id":"2407.05417","title":"See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition","created":"2024-07-07","cited_by_count":14,"area":null},{"id":"2409.17137","title":"PACE: Marrying generalization in PArameter-efficient fine-tuning with Consistency rEgularization","created":"2024-09-25","cited_by_count":14,"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":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2603.14228","title":"Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation","created":"2026-03-15","cited_by_count":14,"area":null},{"id":"2406.03051","title":"Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision","created":"2024-06-05","cited_by_count":13,"area":null},{"id":"2407.08044","title":"RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2407.08056","title":"Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences","created":"2024-07-10","cited_by_count":13,"area":null},{"id":"2408.10774","title":"Flexora: Flexible Low Rank Adaptation for Large Language Models","created":"2024-08-20","cited_by_count":13,"area":null},{"id":"2406.10785","title":"ShareLoRA: Parameter Efficient and Robust Large Language Model Fine-tuning via Shared Low-Rank Adaptation","created":"2024-06-16","cited_by_count":11,"area":null},{"id":"2409.05926","title":"SVFit: Parameter-Efficient Fine-Tuning of Large Pre-Trained Models Using Singular Values","created":"2024-09-09","cited_by_count":11,"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":"2503.16843","title":"LoRASculpt: Sculpting LoRA for Harmonizing General and Specialized Knowledge in Multimodal Large Language Models","created":"2025-03-21","cited_by_count":11,"area":"mllm"},{"id":"2505.20154","title":"UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2512.23017","title":"Merge before Forget: A Single LoRA Continual Learning via Continual Merging","created":"2025-12-28","cited_by_count":11,"area":null},{"id":"2409.11302","title":"Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Models","created":"2024-09-17","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":"2505.20355","title":"GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-05-26","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":"2508.17901","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2510.10432","title":"Hierarchical LoRA MoE for Efficient CTR Model Scaling","created":"2025-10-12","cited_by_count":10,"area":"moe"},{"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":"2401.01752","title":"FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers","created":"2024-01-03","cited_by_count":9,"area":null},{"id":"2405.06368","title":"DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation","created":"2024-05-10","cited_by_count":9,"area":null},{"id":"2406.15480","title":"On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2502.04700","title":"EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference","created":"2025-02-07","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":"2505.22694","title":"MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning","created":"2025-05-28","cited_by_count":9,"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":"2602.02343","title":"Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics","created":"2026-02-02","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":"2406.18082","title":"Octo-planner: On-device Language Model for Planner-Action Agents","created":"2024-06-26","cited_by_count":8,"area":"agents"},{"id":"2410.01870","title":"PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers","created":"2024-10-02","cited_by_count":8,"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":"2412.06071","title":"KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language Models","created":"2024-12-08","cited_by_count":8,"area":null},{"id":"2412.19820","title":"GaLore$+$: Boosting Low-Rank Adaptation for LLMs with Cross-Head Projection","created":"2024-12-15","cited_by_count":8,"area":null},{"id":"2410.00938","title":"MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards","created":"2024-10-01","cited_by_count":7,"area":"moe"},{"id":"2410.03941","title":"AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models","created":"2024-10-04","cited_by_count":7,"area":"diffusion"},{"id":"2410.04060","title":"LoRTA: Low Rank Tensor Adaptation of Large Language Models","created":"2024-10-05","cited_by_count":7,"area":null},{"id":"2410.22782","title":"MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning","created":"2024-10-30","cited_by_count":7,"area":null},{"id":"2501.07890","title":"GRAPHMOE: Amplifying Cognitive Depth of Mixture-of-Experts Network via Introducing Self-Rethinking Mechanism","created":"2025-01-14","cited_by_count":7,"area":"lr"},{"id":"2502.05539","title":"SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation","created":"2025-02-08","cited_by_count":7,"area":null},{"id":"2503.21694","title":"Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data","created":"2025-03-27","cited_by_count":7,"area":"diffusion"},{"id":"2512.04763","title":"MemLoRA: Distilling Expert Adapters for On-Device Memory Systems","created":"2025-12-04","cited_by_count":7,"area":null},{"id":"2410.06431","title":"Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2410.09103","title":"MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2410.13618","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2501.15377","title":"Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation","created":"2025-01-26","cited_by_count":6,"area":null},{"id":"2503.01905","title":"PaCA: Partial Connection Adaptation for Efficient Fine-Tuning","created":"2025-02-28","cited_by_count":6,"area":null},{"id":"2503.12576","title":"RaSA: Rank-Sharing Low-Rank Adaptation","created":"2025-03-16","cited_by_count":6,"area":null},{"id":"2505.20211","title":"PiCa: Parameter-Efficient Fine-Tuning with Column Space Projection","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2507.17706","title":"HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Merging","created":"2025-07-23","cited_by_count":6,"area":null},{"id":"2405.14739","title":"Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning","created":"2024-05-23","cited_by_count":5,"area":null},{"id":"2405.21050","title":"Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion Models","created":"2024-05-31","cited_by_count":5,"area":"diffusion"},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2502.06916","title":"QuIC: Quantum-Inspired Compound Adapters for Parameter Efficient Fine-Tuning","created":"2025-02-10","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}],"next_cursor":"100"}