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 51–75 of 935 papers

TitleStatusHype
KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning—0
CLaDMoP: Learning Transferrable Models from Successful Clinical Trials via LLMsCode0
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation—0
Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models—0
Explain Less, Understand More: Jargon Detection via Personalized Parameter-Efficient Fine-tuning—0
Representation Discrepancy Bridging Method for Remote Sensing Image-Text Retrieval—0
15,500 Seconds: Lean UAV Classification Leveraging PEFT and Pre-Trained NetworksCode0
4,500 Seconds: Small Data Training Approaches for Deep UAV Audio ClassificationCode0
Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Models—0
AdUE: Improving uncertainty estimation head for LoRA adapters in LLMs—0
CoLA: Collaborative Low-Rank AdaptationCode0
Gated Integration of Low-Rank Adaptation for Continual Learning of Language ModelsCode1
VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation—0
Parameter-Efficient Fine-Tuning of Multispectral Foundation Models for Hyperspectral Image Classification—0
Privacy Preserving Conversion Modeling in Data Clean Room—0
Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability HypothesisCode1
Dual Decomposition of Weights and Singular Value Low Rank Adaptation—0
OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation—0
ABBA: Highly Expressive Hadamard Product Adaptation for Large Language ModelsCode1
Efficient Federated Class-Incremental Learning of Pre-Trained Models via Task-agnostic Low-rank Residual Adaptation—0
Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection—0
SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization—0
Exploring Sparsity for Parameter Efficient Fine Tuning Using WaveletsCode0
Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptation—0
Memory-Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation—0
Show:102550
← PrevPage 3 of 38Next →
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