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 201–250 of 935 papers

TitleStatusHype
Parameter-Efficient Fine-Tuning of State Space ModelsCode1
Hydra: Multi-head Low-rank Adaptation for Parameter Efficient Fine-tuningCode1
HiFT: A Hierarchical Full Parameter Fine-Tuning StrategyCode1
APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and InferenceCode1
Parameter-efficient Multi-task Fine-tuning for Transformers via Shared HypernetworksCode1
Hyperdecoders: Instance-specific decoders for multi-task NLPCode1
AdapterGNN: Parameter-Efficient Fine-Tuning Improves Generalization in GNNsCode1
Ferret: Federated Full-Parameter Tuning at Scale for Large Language ModelsCode1
A Prompt Learning Framework for Source Code SummarizationCode1
Positional Prompt Tuning for Efficient 3D Representation LearningCode1
HALO: Hadamard-Assisted Lower-Precision Optimization for LLMsCode1
LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-TuningCode1
PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task AdaptationCode1
Expanding Sparse Tuning for Low Memory UsageCode1
BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelsCode1
Reasoning on a Budget: Miniaturizing DeepSeek R1 with SFT-GRPO Alignment for Instruction-Tuned LLMsCode1
AlphaLoRA: Assigning LoRA Experts Based on Layer Training QualityCode1
Rethinking Addressing in Language Models via Contexualized Equivariant Positional EncodingCode1
Riemannian Preconditioned LoRA for Fine-Tuning Foundation ModelsCode1
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion ModelsCode1
TS-SAM: Fine-Tuning Segment-Anything Model for Downstream TasksCode1
Gradient-based Parameter Selection for Efficient Fine-TuningCode1
Harnessing Large Language Models for Text-Rich Sequential RecommendationCode1
IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFTCode1
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of AdaptersCode1
Scaling & Shifting Your Features: A New Baseline for Efficient Model TuningCode1
CL-LoRA: Continual Low-Rank Adaptation for Rehearsal-Free Class-Incremental LearningCode1
Generative Parameter-Efficient Fine-TuningCode1
Gated Integration of Low-Rank Adaptation for Continual Learning of Language ModelsCode1
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision ModelCode1
Density Adaptive Attention is All You Need: Robust Parameter-Efficient Fine-Tuning Across Multiple ModalitiesCode1
Efficient Test Time Adapter Ensembling for Low-resource Language VarietiesCode1
GIST: Improving Parameter Efficient Fine Tuning via Knowledge InteractionCode1
FonTS: Text Rendering with Typography and Style ControlsCode1
C2A: Client-Customized Adaptation for Parameter-Efficient Federated LearningCode1
SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language ModelsCode1
Sparse is Enough in Fine-tuning Pre-trained Large Language ModelsCode1
FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 ClassesCode1
Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 KilobytesCode1
Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting ModelsCode1
MoSA: Mixture of Sparse Adapters for Visual Efficient TuningCode1
SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual TrackingCode1
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space ModelsCode1
SUR-adapter: Enhancing Text-to-Image Pre-trained Diffusion Models with Large Language ModelsCode1
ABBA: Highly Expressive Hadamard Product Adaptation for Large Language ModelsCode1
KIF: Knowledge Identification and Fusion for Language Model Continual LearningCode1
An Empirical Study on Parameter-Efficient Fine-Tuning for MultiModal Large Language ModelsCode1
Towards a General Framework for Continual Learning with Pre-trainingCode1
Towards Efficient Visual-Language Alignment of the Q-Former for Visual Reasoning TasksCode1
Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank StructuresCode1
Show:102550
← PrevPage 5 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