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 151–200 of 935 papers

TitleStatusHype
Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language ModelsCode1
SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language ModelsCode1
Sparse Matrix in Large Language Model Fine-tuningCode1
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector BanksCode1
FLoRA: Low-Rank Core Space for N-dimensionCode1
Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and InferenceCode1
Spectral Adapter: Fine-Tuning in Spectral SpaceCode1
MeteoRA: Multiple-tasks Embedded LoRA for Large Language ModelsCode1
Parameter-Efficient Instance-Adaptive Neural Video CompressionCode1
Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuningCode1
LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical ReportCode1
Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic ForgettingCode1
Simple, Efficient and Scalable Structure-aware Adapter Boosts Protein Language ModelsCode1
Towards More General Video-based Deepfake Detection through Facial Feature Guided Adaptation for Foundation ModelCode1
Mixture of Low-rank Experts for Transferable AI-Generated Image DetectionCode1
IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFTCode1
Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design ApproachCode1
ILLUMINER: Instruction-tuned Large Language Models as Few-shot Intent Classifier and Slot FillerCode1
Harnessing Large Language Models for Text-Rich Sequential RecommendationCode1
PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task AdaptationCode1
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated ExpertsCode1
FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 ClassesCode1
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward PropagationCode1
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-TuningCode1
Asymmetry in Low-Rank Adapters of Foundation ModelsCode1
Multimodal Instruction Tuning with Conditional Mixture of LoRACode1
Advancing Parameter Efficiency in Fine-tuning via Representation EditingCode1
KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text DetectionCode1
LoRETTA: Low-Rank Economic Tensor-Train Adaptation for Ultra-Low-Parameter Fine-Tuning of Large Language ModelsCode1
TuneTables: Context Optimization for Scalable Prior-Data Fitted NetworksCode1
UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language ModelsCode1
Open-Vocabulary Calibration for Fine-tuned CLIPCode1
Democratizing Large Language Models via Personalized Parameter-Efficient Fine-tuningCode1
Riemannian Preconditioned LoRA for Fine-Tuning Foundation ModelsCode1
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of AdaptersCode1
Scaling Sparse Fine-Tuning to Large Language ModelsCode1
HiFT: A Hierarchical Full Parameter Fine-Tuning StrategyCode1
Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation ModelsCode1
APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and InferenceCode1
Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple ModalitiesCode1
A Prompt Learning Framework for Source Code SummarizationCode1
RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program RepairCode1
Sparse is Enough in Fine-tuning Pre-trained Large Language ModelsCode1
SA^2VP: Spatially Aligned-and-Adapted Visual PromptCode1
Gradient-based Parameter Selection for Efficient Fine-TuningCode1
Extending Whisper with prompt tuning to target-speaker ASRCode1
GIST: Improving Parameter Efficient Fine Tuning via Knowledge InteractionCode1
Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 KilobytesCode1
MoSA: Mixture of Sparse Adapters for Visual Efficient TuningCode1
Evaluating General Purpose Vision Foundation Models for Medical Image Analysis: An Experimental Study of DINOv2 on Radiology BenchmarksCode1
Show:102550
← PrevPage 4 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