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 101–150 of 935 papers

TitleStatusHype
Efficient Localized Adaptation of Neural Weather Forecasting: A Case Study in the MENA RegionCode1
Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank StructuresCode1
AutoVP: An Automated Visual Prompting Framework and BenchmarkCode1
Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language ModelsCode1
Extending Whisper with prompt tuning to target-speaker ASRCode1
Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 KilobytesCode1
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelsCode1
AlphaLoRA: Assigning LoRA Experts Based on Layer Training QualityCode1
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model TuningCode1
MapSAM: Adapting Segment Anything Model for Automated Feature Detection in Historical MapsCode1
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsCode1
Ferret: Federated Full-Parameter Tuning at Scale for Large Language ModelsCode1
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-TuningCode1
Advancing Parameter Efficiency in Fine-tuning via Representation EditingCode1
LLM-based Medical Assistant Personalization with Short- and Long-Term Memory CoordinationCode1
Efficient Self-Supervised Adaptation for Medical Image AnalysisCode1
LoRA Soups: Merging LoRAs for Practical Skill Composition TasksCode1
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-TuningCode1
LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual LearningCode1
FonTS: Text Rendering with Typography and Style ControlsCode1
Asymmetry in Low-Rank Adapters of Foundation ModelsCode1
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision ModelCode1
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language ModelsCode1
Gated Integration of Low-Rank Adaptation for Continual Learning of Language ModelsCode1
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward PropagationCode1
Generative Parameter-Efficient Fine-TuningCode1
Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot LearningCode1
LiST: Lite Prompted Self-training Makes Parameter-Efficient Few-shot LearnersCode1
LoFiT: Localized Fine-tuning on LLM RepresentationsCode1
Do Vision Foundation Models Enhance Domain Generalization in Medical Image Segmentation?Code1
LoKI: Low-damage Knowledge Implanting of Large Language ModelsCode1
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical ReportCode1
Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation ModelsCode1
Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual RecognitionCode1
KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text DetectionCode1
Embedded Prompt Tuning: Towards Enhanced Calibration of Pretrained Models for Medical ImagesCode1
Joint Localization and Activation Editing for Low-Resource Fine-TuningCode1
DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-TuningCode1
KaSA: Knowledge-Aware Singular-Value Adaptation of Large Language ModelsCode1
ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and QuantizationCode1
IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuningCode1
A Comprehensive Analysis of Adapter EfficiencyCode1
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuningCode1
KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge DistillationCode1
Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early PruningCode1
Domain Generalization Using Large Pretrained Models with Mixture-of-AdaptersCode1
Content-based Controls For Music Large Language ModelingCode1
DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuningCode1
IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion ModelsCode1
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion ModelsCode1
Show:102550
← PrevPage 3 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