SOTAVerified

parameter-efficient fine-tuning

Parameter-Efficient Fine-Tuning (PEFT) is a technique used to adapt pre-trained models to new tasks with minimal changes to the model's parameters. This approach is particularly useful in scenarios where computational resources are limited or when it is desirable to maintain the original model's performance on the initial task.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 701–750 of 935 papers

TitleStatusHype
LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation—0
Learning to Route Among Specialized Experts for Zero-Shot GeneralizationCode2
L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models—0
Open-Vocabulary Calibration for Fine-tuned CLIPCode1
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuningCode1
Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning—0
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric LearningCode0
Riemannian Preconditioned LoRA for Fine-Tuning Foundation ModelsCode1
Enhancing the efficiency of protein language models with minimal wet-lab data through few-shot learning—0
Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A SurveyCode4
From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in TransformersCode0
LoTR: Low Tensor Rank Weight Adaptation—0
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of AdaptersCode1
Hi-SAM: Marrying Segment Anything Model for Hierarchical Text SegmentationCode3
Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model—0
Scaling Sparse Fine-Tuning to Large Language ModelsCode1
X-PEFT: eXtremely Parameter-Efficient Fine-Tuning for Extreme Multi-Profile Scenarios—0
HiFT: A Hierarchical Full Parameter Fine-Tuning StrategyCode1
The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness—0
APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and InferenceCode1
Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation ModelsCode1
PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation—0
Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple ModalitiesCode1
OrchMoE: Efficient Multi-Adapter Learning with Task-Skill Synergy—0
FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis—0
Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers—0
Improving Domain Adaptation through Extended-Text Reading Comprehension—0
Scaling Laws for Forgetting When Fine-Tuning Large Language Models—0
Chain of History: Learning and Forecasting with LLMs for Temporal Knowledge Graph Completion—0
A Survey on Efficient Federated Learning Methods for Foundation Model Training—0
RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust AdaptationCode3
Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning—0
PeFoMed: Parameter Efficient Fine-tuning of Multimodal Large Language Models for Medical ImagingCode2
ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic SegmentationCode2
PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble TechniquesCode0
Navigating Uncertainty: Optimizing API Dependency for Hallucination Reduction in Closed-Book Question Answering—0
MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task LearningCode2
Astraios: Parameter-Efficient Instruction Tuning Code Large Language ModelsCode5
Black-Box Tuning of Vision-Language Models with Effective Gradient ApproximationCode0
A Prompt Learning Framework for Source Code SummarizationCode1
A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering TasksCode0
RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program RepairCode1
A Split-and-Privatize Framework for Large Language Model Fine-Tuning—0
Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers—0
Fast-NTK: Parameter-Efficient Unlearning for Large-Scale Models—0
Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment—0
Sparse is Enough in Fine-tuning Pre-trained Large Language ModelsCode1
Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability—0
SA^2VP: Spatially Aligned-and-Adapted Visual PromptCode1
Gradient-based Parameter Selection for Efficient Fine-TuningCode1
Show:102550
← PrevPage 15 of 19Next →
All datasetsBoolQHellaSwagWinoGrande

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1LLaMA2-7bAccuracy (% )82.63—Unverified
2LLaMA2-7bAccuracy (% )82.63—Unverified
3LLaMA2-7bAccuracy (% )81.93—Unverified
4LLaMA2-7bAccuracy (% )80.28—Unverified
#ModelMetricClaimedVerifiedStatus
1LLaMA2-7bAccuracy (% )76.68—Unverified
2LLaMA2-7bAccuracy (% )76.67—Unverified
3LLaMA2-7bAccuracy (% )76.27—Unverified
#ModelMetricClaimedVerifiedStatus
1LLaMA2-7bAccuracy (% )70.8—Unverified
2LLaMA2-7bAccuracy (% )70.09—Unverified
3LLaMA2-7bAccuracy (% )69.85—Unverified