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 851–900 of 935 papers

TitleStatusHype
Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain GeneralizationCode0
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric LearningCode0
Layer-wise Importance Matters: Less Memory for Better Performance in Parameter-efficient Fine-tuning of Large Language ModelsCode0
DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language ModelsCode0
DLP: Dynamic Layerwise Pruning in Large Language ModelsCode0
Label Privacy in Split Learning for Large Models with Parameter-Efficient TrainingCode0
BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language ModelsCode0
SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language ExplanationsCode0
SparseGrad: A Selective Method for Efficient Fine-tuning of MLP LayersCode0
KIND: Knowledge Integration and Diversion for Training Decomposable ModelsCode0
SAN: Hypothesizing Long-Term Synaptic Development and Neural Engram Mechanism in Scalable Model's Parameter-Efficient Fine-TuningCode0
Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning DynamicsCode0
Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language ModelsCode0
Benchmarking Pathology Foundation Models: Adaptation Strategies and ScenariosCode0
Privacy-Preserved Automated Scoring using Federated Learning for Educational ResearchCode0
Deepfakes on Demand: the rise of accessible non-consensual deepfake image generatorsCode0
Bayesian Parameter-Efficient Fine-Tuning for Overcoming Catastrophic ForgettingCode0
Sparsity May Be All You Need: Sparse Random Parameter AdaptationCode0
Deep Content Understanding Toward Entity and Aspect Target Sentiment Analysis on Foundation ModelsCode0
Spectral-Aware Low-Rank Adaptation for Speaker VerificationCode0
Spectrum-Aware Parameter Efficient Fine-Tuning for Diffusion ModelsCode0
DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned ModelsCode0
KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep HashingCode0
Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged AnnotationsCode0
Speech Translation Refinement using Large Language ModelsCode0
Prompt to be Consistent is Better than Self-Consistent? Few-Shot and Zero-Shot Fact Verification with Pre-trained Language ModelsCode0
4,500 Seconds: Small Data Training Approaches for Deep UAV Audio ClassificationCode0
Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt AdaptationCode0
CustomTTT: Motion and Appearance Customized Video Generation via Test-Time TrainingCode0
Is Modularity Transferable? A Case Study through the Lens of Knowledge DistillationCode0
Prototype-based HyperAdapter for Sample-Efficient Multi-task TuningCode0
Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank BottlenecksCode0
PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt TuningCode0
Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised ModelsCode0
Interweaving Memories of a Siamese Large Language ModelCode0
Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTexCode0
QEFT: Quantization for Efficient Fine-Tuning of LLMsCode0
CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential RecommendationCode0
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning ParadigmCode0
InstructAV: Instruction Fine-tuning Large Language Models for Authorship VerificationCode0
ASteISR: Adapting Single Image Super-resolution Pre-trained Model for Efficient Stereo Image Super-resolutionCode0
QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation DecompositionCode0
Improving generalization in large language models by learning prefix subspacesCode0
Updating CLIP to Prefer Descriptions Over CaptionsCode0
Conversational Factor Information Retrieval Model (ConFIRM)Code0
STAR: Constraint LoRA with Dynamic Active Learning for Data-Efficient Fine-Tuning of Large Language ModelsCode0
Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classificationCode0
Question answering system of bridge design specification based on large language modelCode0
Step-by-Step Unmasking for Parameter-Efficient Fine-tuning of Large Language ModelsCode0
RadAdapt: Radiology Report Summarization via Lightweight Domain Adaptation of Large Language ModelsCode0
Show:102550
← PrevPage 18 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