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 301–350 of 935 papers

TitleStatusHype
Efficient Federated Split Learning for Large Language Models over Communication Networks—0
Block Expanded DINORET: Adapting Natural Domain Foundation Models for Retinal Imaging Without Catastrophic Forgetting—0
AMR Parsing with Instruction Fine-tuned Pre-trained Language Models—0
Lifelong Learning with Task-Specific Adaptation: Addressing the Stability-Plasticity Dilemma—0
LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuning—0
Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout—0
Efficient Federated Class-Incremental Learning of Pre-Trained Models via Task-agnostic Low-rank Residual Adaptation—0
Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition—0
Efficient Differentially Private Fine-Tuning of Diffusion Models—0
AlphaTuning: Quantization-Aware Parameter-Efficient Adaptation of Large-Scale Pre-Trained Language Models—0
Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision—0
Efficient Deployment of Large Language Models on Resource-constrained Devices—0
Efficient Continual Adaptation of Pretrained Robotic Policy with Online Meta-Learned Adapters—0
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models—0
Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation—0
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models—0
Memory-Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation—0
Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy—0
Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation—0
BiSup: Bidirectional Quantization Error Suppression for Large Language Models—0
Efficient Adaptation For Remote Sensing Visual Grounding—0
Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models—0
BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models—0
A LoRA is Worth a Thousand Pictures—0
Efficiency at Scale: Investigating the Performance of Diminutive Language Models in Clinical Tasks—0
EEG-Based Mental Imagery Task Adaptation via Ensemble of Weight-Decomposed Low-Rank Adapters—0
BioInstruct: Instruction Tuning of Large Language Models for Biomedical Natural Language Processing—0
BiLoRA: Almost-Orthogonal Parameter Spaces for Continual Learning—0
ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models—0
Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization—0
LayerNorm: A key component in parameter-efficient fine-tuning—0
Bilevel ZOFO: Bridging Parameter-Efficient and Zeroth-Order Techniques for Efficient LLM Fine-Tuning and Meta-Training—0
Aligner: One Global Token is Worth Millions of Parameters When Aligning Large Language Models—0
BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation—0
Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning—0
A Hessian-informed hyperparameter optimization for differential learning rate—0
Dual Low-Rank Adaptation for Continual Learning with Pre-Trained Models—0
KerZOO: Kernel Function Informed Zeroth-Order Optimization for Accurate and Accelerated LLM Fine-Tuning—0
Dual Decomposition of Weights and Singular Value Low Rank Adaptation—0
Keep the Balance: A Parameter-Efficient Symmetrical Framework for RGB+X Semantic Segmentation—0
L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models—0
DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation—0
Beyond LoRA: Exploring Efficient Fine-Tuning Techniques for Time Series Foundational Models—0
Adapter-Based Extension of Multi-Speaker Text-to-Speech Model for New Speakers—0
Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs—0
BeamLoRA: Beam-Constraint Low-Rank Adaptation—0
Ahead-of-Time P-Tuning—0
LACoS-BLOOM: Low-rank Adaptation with Contrastive objective on 8 bits Siamese-BLOOM—0
Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models—0
LLMI3D: Empowering LLM with 3D Perception from a Single 2D Image—0
Show:102550
← PrevPage 7 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