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 51–100 of 935 papers

TitleStatusHype
mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUsCode2
MTLoRA: A Low-Rank Adaptation Approach for Efficient Multi-Task LearningCode2
GlyphDraw: Seamlessly Rendering Text with Intricate Spatial Structures in Text-to-Image GenerationCode2
One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuningCode2
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization AlignmentCode2
LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank AdaptationCode2
Memory-Space Visual Prompting for Efficient Vision-Language Fine-TuningCode2
Parameter-Efficient Fine-Tuning for Foundation ModelsCode2
LoRA: Low-Rank Adaptation of Large Language ModelsCode2
LoRA-Pro: Are Low-Rank Adapters Properly Optimized?Code2
Low-Rank Quantization-Aware Training for LLMsCode2
Any2Point: Empowering Any-modality Large Models for Efficient 3D UnderstandingCode2
ClassWise-SAM-Adapter: Parameter Efficient Fine-tuning Adapts Segment Anything to SAR Domain for Semantic SegmentationCode2
CoLLiE: Collaborative Training of Large Language Models in an Efficient WayCode2
Balancing LoRA Performance and Efficiency with Simple Shard SharingCode2
Learning to Route Among Specialized Experts for Zero-Shot GeneralizationCode2
LoRA-XS: Low-Rank Adaptation with Extremely Small Number of ParametersCode2
FairMedFM: Fairness Benchmarking for Medical Imaging Foundation ModelsCode2
AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-TuningCode1
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language ModelsCode1
I-MedSAM: Implicit Medical Image Segmentation with Segment AnythingCode1
ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot FillerCode1
Imaging foundation model for universal enhancement of non-ideal measurement CTCode1
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuningCode1
Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuningCode1
Hyperdecoders: Instance-specific decoders for multi-task NLPCode1
HiFT: A Hierarchical Full Parameter Fine-Tuning StrategyCode1
Harnessing Large Language Models for Text-Rich Sequential RecommendationCode1
IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFTCode1
IncreLoRA: Incremental Parameter Allocation Method for Parameter-Efficient Fine-tuningCode1
GIST: Improving Parameter Efficient Fine Tuning via Knowledge InteractionCode1
AlphaLoRA: Assigning LoRA Experts Based on Layer Training QualityCode1
Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple ModalitiesCode1
AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNsCode1
Generative Parameter-Efficient Fine-TuningCode1
Gradient-based Parameter Selection for Efficient Fine-TuningCode1
Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting ModelsCode1
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision ModelCode1
FLoRA: Low-Rank Core Space for N-dimensionCode1
C2A: Client-Customized Adaptation for Parameter-Efficient Federated LearningCode1
FonTS: Text Rendering with Typography and Style ControlsCode1
Gated Integration of Low-Rank Adaptation for Continual Learning of Language ModelsCode1
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMsCode1
Extending Whisper with prompt tuning to target-speaker ASRCode1
FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image AnalysisCode1
AutoVP: An Automated Visual Prompting Framework and BenchmarkCode1
Aggregate, Decompose, and Fine-Tune: A Simple Yet Effective Factor-Tuning Method for Vision TransformerCode1
FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 ClassesCode1
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model TuningCode1
AdaMix: Mixture-of-Adaptations for Parameter-efficient Model TuningCode1
Show:102550
← PrevPage 2 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