{"total":139,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380,"area":null},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915,"area":null},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2310.11454","title":"VeRA: Vector-based Random Matrix Adaptation","created":"2023-10-17","cited_by_count":300,"area":null},{"id":"2404.02948","title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models","created":"2024-04-03","cited_by_count":269,"area":null},{"id":"2305.03048","title":"Personalize Segment Anything Model with One Shot","created":"2023-05-04","cited_by_count":250,"area":null},{"id":"2312.12148","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","created":"2023-12-19","cited_by_count":230,"area":null},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133,"area":null},{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"area":null},{"id":"2402.11592","title":"Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark","created":"2024-02-18","cited_by_count":114,"area":null},{"id":"2402.03293","title":"Flora: Low-Rank Adapters Are Secretly Gradient Compressors","created":"2024-02-05","cited_by_count":108,"area":null},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100,"area":null},{"id":"2305.05726","title":"Vision-Language Models in Remote Sensing: Current Progress and Future Trends","created":"2023-05-09","cited_by_count":93,"area":"mllm"},{"id":"2405.03003","title":"Parameter-Efficient Fine-Tuning with Discrete Fourier Transform","created":"2024-05-05","cited_by_count":71,"area":null},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70,"area":null},{"id":"2301.01821","title":"Parameter-Efficient Fine-Tuning Design Spaces","created":"2023-01-04","cited_by_count":67,"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":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64,"area":null},{"id":"2402.15751","title":"Sparse MeZO: Less Parameters for Better Performance in Zeroth-Order LLM Fine-Tuning","created":"2024-02-24","cited_by_count":54,"area":null},{"id":"2207.14381","title":"Pro-tuning: Unified Prompt Tuning for Vision Tasks","created":"2022-07-28","cited_by_count":53,"area":null},{"id":"2404.14779","title":"Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches","created":"2024-04-23","cited_by_count":52,"area":null},{"id":"2406.03372","title":"Training of Physical Neural Networks","created":"2024-06-05","cited_by_count":49,"area":null},{"id":"2210.00036","title":"Differentially Private Bias-Term Fine-tuning of Foundation Models","created":"2022-09-30","cited_by_count":48,"area":null},{"id":"2403.01849","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","created":"2024-03-04","cited_by_count":48,"area":"mllm"},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"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":"2204.13031","title":"DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation","created":"2022-04-27","cited_by_count":35,"area":null},{"id":"2309.03118","title":"Knowledge Solver: Teaching LLMs to Search for Domain Knowledge from Knowledge Graphs","created":"2023-09-06","cited_by_count":35,"area":null},{"id":"2203.03131","title":"Input-Tuning: Adapting Unfamiliar Inputs to Frozen Pretrained Models","created":"2022-03-07","cited_by_count":34,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2101.04640","title":"Dimensions of Commonsense Knowledge","created":"2021-01-12","cited_by_count":29,"area":null},{"id":"2106.02205","title":"Enabling Lightweight Fine-tuning for Pre-trained Language Model Compression based on Matrix Product Operators","created":"2021-06-04","cited_by_count":29,"area":null},{"id":"2310.02556","title":"NOLA: Compressing LoRA using Linear Combination of Random Basis","created":"2023-10-04","cited_by_count":29,"area":null},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2210.00788","title":"Towards a Unified View on Visual Parameter-Efficient Transfer Learning","created":"2022-10-03","cited_by_count":25,"area":null},{"id":"2305.16597","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","created":"2023-05-26","cited_by_count":25,"area":null},{"id":"2305.01146","title":"RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language Models","created":"2023-05-02","cited_by_count":24,"area":null},{"id":"2204.13362","title":"Tailor: A Prompt-Based Approach to Attribute-Based Controlled Text Generation","created":"2022-04-28","cited_by_count":22,"area":null},{"id":"2303.09992","title":"LION: Implicit Vision Prompt Tuning","created":"2023-03-17","cited_by_count":22,"area":null},{"id":"2204.12785","title":"Plug-and-Play Adaptation for Continuously-updated QA","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2308.08810","title":"Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts","created":"2023-08-17","cited_by_count":21,"area":null},{"id":"2405.13952","title":"Spectral Adapter: Fine-Tuning in Spectral Space","created":"2024-05-22","cited_by_count":21,"area":null},{"id":"2304.08109","title":"A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model","created":"2023-04-17","cited_by_count":19,"area":null},{"id":"2405.10216","title":"Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting","created":"2024-05-16","cited_by_count":18,"area":null},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2410.09437","title":"MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning","created":"2024-10-12","cited_by_count":17,"area":null},{"id":"2305.16651","title":"TADA: Task-Agnostic Dialect Adapters for English","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2410.02200","title":"Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2207.03509","title":"Meta-Learning the Difference: Preparing Large Language Models for Efficient Adaptation","created":"2022-07-07","cited_by_count":14,"area":null},{"id":"2208.08176","title":"Visual Comparison of Language Model Adaptation","created":"2022-08-17","cited_by_count":14,"area":null},{"id":"2306.00618","title":"Effective Structured Prompting by Meta-Learning and Representative Verbalizer","created":"2023-06-01","cited_by_count":14,"area":null},{"id":"2408.01008","title":"Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs","created":"2024-08-02","cited_by_count":14,"area":null},{"id":"2409.10927","title":"Propulsion: Steering LLM with Tiny Fine-Tuning","created":"2024-09-17","cited_by_count":14,"area":null},{"id":"2410.20650","title":"NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2211.01979","title":"Tiny-Attention Adapter: Contexts Are More Important Than the Number of Parameters","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2407.11033","title":"Hadamard Adapter: An Extreme Parameter-Efficient Adapter Tuning Method for Pre-trained Language Models","created":"2024-07-04","cited_by_count":13,"area":null},{"id":"2401.15207","title":"HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy","created":"2024-01-26","cited_by_count":12,"area":null},{"id":"2204.03357","title":"Parameter-Efficient Abstractive Question Answering over Tables or Text","created":"2022-04-07","cited_by_count":11,"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":"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":"2407.09946","title":"Low-Rank Interconnected Adaptation across Layers","created":"2024-07-13","cited_by_count":10,"area":null},{"id":"2310.01818","title":"AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework","created":"2023-10-03","cited_by_count":9,"area":null},{"id":"2402.15414","title":"Does Combining Parameter-efficient Modules Improve Few-shot Transfer Accuracy?","created":"2024-02-23","cited_by_count":9,"area":null},{"id":"2505.18877","title":"RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models","created":"2025-05-24","cited_by_count":9,"area":null},{"id":"2602.06204","title":"Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning","created":"2026-02-05","cited_by_count":9,"area":null},{"id":"2307.05468","title":"My3DGen: A Scalable Personalized 3D Generative Model","created":"2023-07-11","cited_by_count":8,"area":null},{"id":"2401.04339","title":"Memory-Efficient Fine-Tuning for Quantized Diffusion Model","created":"2024-01-09","cited_by_count":8,"area":"diffusion"},{"id":"2403.13037","title":"BiLoRA: A Bi-level Optimization Framework for Overfitting-Resilient Low-Rank Adaptation of Large Pre-trained Models","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2408.10715","title":"Fine-Tuning a Local LLaMA-3 Large Language Model for Automated Privacy-Preserving Physician Letter Generation in Radiation Oncology","created":"2024-08-20","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":"2308.05426","title":"Adaptive Low Rank Adaptation of Segment Anything to Salient Object Detection","created":"2023-08-10","cited_by_count":7,"area":null},{"id":"2404.09027","title":"MING-MOE: Enhancing Medical Multi-Task Learning in Large Language Models with Sparse Mixture of Low-Rank Adapter Experts","created":"2024-04-13","cited_by_count":7,"area":"moe"},{"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":"2410.10870","title":"PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2502.05539","title":"SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation","created":"2025-02-08","cited_by_count":7,"area":null},{"id":"2505.09395","title":"Quantum-Enhanced Parameter-Efficient Learning for Typhoon Trajectory Forecasting","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2205.03720","title":"Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention","created":"2022-05-07","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":"2211.16164","title":"Few-shot Query-Focused Summarization with Prefix-Merging","created":"2022-11-29","cited_by_count":5,"area":null},{"id":"2309.03412","title":"From Base to Conversational: Japanese Instruction Dataset and Tuning Large Language Models","created":"2023-09-07","cited_by_count":5,"area":null},{"id":"2409.00055","title":"SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models","created":"2024-08-21","cited_by_count":5,"area":null},{"id":"2503.11144","title":"MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling","created":"2025-03-14","cited_by_count":5,"area":"moe"},{"id":"2505.23724","title":"SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2203.01146","title":"Controlling the Focus of Pretrained Language Generation Models","created":"2022-03-02","cited_by_count":4,"area":null},{"id":"2310.15541","title":"Improving Language Models Meaning Understanding and Consistency by Learning Conceptual Roles from Dictionary","created":"2023-10-24","cited_by_count":4,"area":null},{"id":"2403.09377","title":"Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2405.19670","title":"One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models","created":"2024-05-30","cited_by_count":4,"area":"rag"},{"id":"2406.17484","title":"MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2410.09758","title":"BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation","created":"2024-10-13","cited_by_count":4,"area":null},{"id":"2502.06820","title":"LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning","created":"2025-02-05","cited_by_count":4,"area":null},{"id":"2601.09361","title":"GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR","created":"2026-01-14","cited_by_count":4,"area":"lr"},{"id":"2210.14469","title":"Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2301.13268","title":"Contextual Dynamic Prompting for Response Generation in Task-oriented Dialog Systems","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2303.13220","title":"Parameter-Efficient Sparse Retrievers and Rerankers using Adapters","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2307.08189","title":"Mini-Giants: \"Small\" Language Models and Open Source Win-Win","created":"2023-07-17","cited_by_count":3,"area":null},{"id":"2403.00625","title":"Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency","created":"2024-03-01","cited_by_count":3,"area":null}],"next_cursor":"100"}