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 351–400 of 935 papers

TitleStatusHype
Improving LoRA in Privacy-preserving Federated Learning—0
BeamLoRA: Beam-Constraint Low-Rank Adaptation—0
Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning—0
Ahead-of-Time P-Tuning—0
Improving Domain Adaptation through Extended-Text Reading Comprehension—0
Low-Rank Adapters Meet Neural Architecture Search for LLM Compression—0
Does Combining Parameter-efficient Modules Improve Few-shot Transfer Accuracy?—0
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates—0
LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement—0
Balancing Stability and Plasticity in Pretrained Detector: A Dual-Path Framework for Incremental Object Detection—0
A GEN AI Framework for Medical Note Generation—0
LoRA ensembles for large language model fine-tuning—0
LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs—0
DLoRA: Distributed Parameter-Efficient Fine-Tuning Solution for Large Language Model—0
HyperLoader: Integrating Hypernetwork-Based LoRA and Adapter Layers into Multi-Task Transformers for Sequence Labelling—0
AutoPsyC: Automatic Recognition of Psychodynamic Conflicts from Semi-structured Interviews with Large Language Models—0
Hyper Compressed Fine-Tuning of Large Foundation Models with Quantum Inspired Adapters—0
DiffuseKronA: A Parameter Efficient Fine-tuning Method for Personalized Diffusion Models—0
DiffoRA: Enabling Parameter-Efficient LLM Fine-Tuning via Differential Low-Rank Matrix Adaptation—0
AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models—0
HUT: A More Computation Efficient Fine-Tuning Method With Hadamard Updated Transformation—0
Hypernetworks for Personalizing ASR to Atypical Speech—0
HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks—0
HyperTuning: Toward Adapting Large Language Models without Back-propagation—0
Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer—0
IAPT: Instruction-Aware Prompt Tuning for Large Language Models—0
ICL Markup: Structuring In-Context Learning using Soft-Token Tags—0
iConFormer: Dynamic Parameter-Efficient Tuning with Input-Conditioned Adaptation—0
HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models—0
HSACNet: Hierarchical Scale-Aware Consistency Regularized Semi-Supervised Change Detection—0
Differentially Private Fine-Tuning of Diffusion Models—0
AdaFish: Fast low-rank parameter-efficient fine-tuning by using second-order information—0
House of Cards: Massive Weights in LLMs—0
HM3: Heterogeneous Multi-Class Model Merging—0
DiDOTS: Knowledge Distillation from Large-Language-Models for Dementia Obfuscation in Transcribed Speech—0
HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation—0
Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models—0
A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judge—0
LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation—0
High-Accuracy ECG Image Interpretation using Parameter-Efficient LoRA Fine-Tuning with Multimodal LLaMA 3.2—0
DESIRE: Dynamic Knowledge Consolidation for Rehearsal-Free Continual Learning—0
HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models—0
HiFi: High-Information Attention Heads Hold for Parameter-Efficient Model Adaptation—0
InfoSAM: Fine-Tuning the Segment Anything Model from An Information-Theoretic Perspective—0
DP-DyLoRA: Fine-Tuning Transformer-Based Models On-Device under Differentially Private Federated Learning using Dynamic Low-Rank Adaptation—0
AuroRA: Breaking Low-Rank Bottleneck of LoRA with Nonlinear Mapping—0
HeLM: Highlighted Evidence augmented Language Model for Enhanced Table-to-Text Generation—0
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning—0
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimization—0
HD-PiSSA: High-Rank Distributed Orthogonal Adaptation—0
Show:102550
← PrevPage 8 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