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 376–400 of 935 papers

TitleStatusHype
Parameter Efficient Fine-tuning via Explained Variance AdaptationCode1
PortLLM: Personalizing Evolving Large Language Models with Training-Free and Portable Model Patches—0
CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection—0
Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?Code0
QERA: an Analytical Framework for Quantization Error Reconstruction—0
DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech—0
LoRTA: Low Rank Tensor Adaptation of Large Language Models—0
BIPEFT: Budget-Guided Iterative Search for Parameter Efficient Fine-Tuning of Large Pretrained Language Models—0
Adapting Segment Anything Model to Melanoma Segmentation in Microscopy Slide Images—0
Llama SLayer 8B: Shallow Layers Hold the Key to Knowledge InjectionCode0
NEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained Models—0
House of Cards: Massive Weights in LLMs—0
TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language ModelsCode1
Imaging foundation model for universal enhancement of non-ideal measurement CTCode1
DLP-LoRA: Efficient Task-Specific LoRA Fusion with a Dynamic, Lightweight Plugin for Large Language ModelsCode0
SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models—0
Embedding-based statistical inference on generative models—0
Unsupervised Human Preference Learning—0
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language ModelsCode0
Resource Allocation for Stable LLM Training in Mobile Edge Computing—0
Vision-Language Models are Strong Noisy Label DetectorsCode1
Pear: Pruning and Sharing Adapters in Visual Parameter-Efficient Fine-TuningCode0
FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models—0
A GEN AI Framework for Medical Note Generation—0
HM3: Heterogeneous Multi-Class Model Merging—0
Show:102550
← PrevPage 16 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