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 151–200 of 935 papers

TitleStatusHype
FedSCA: Federated Tuning with Similarity-guided Collaborative Aggregation for Heterogeneous Medical Image Segmentation—0
Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam TasksCode1
MAST-Pro: Dynamic Mixture-of-Experts for Adaptive Segmentation of Pan-Tumors with Knowledge-Driven Prompts—0
Quantum-Enhanced LLM Efficient Fine Tuning—0
A Survey on Federated Fine-tuning of Large Language ModelsCode2
Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding—0
MoLEx: Mixture of Layer Experts for Finetuning with Sparse UpcyclingCode0
Rethinking Few-Shot Adaptation of Vision-Language Models in Two StagesCode1
Enhancing Aviation Communication Transcription: Fine-Tuning Distil-Whisper with LoRA—0
Singular Value Fine-tuning for Few-Shot Class-Incremental Learning—0
Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout—0
Privacy-Preserved Automated Scoring using Federated Learning for Educational ResearchCode0
Enhanced Continual Learning of Vision-Language Models with Model Fusion—0
Revisiting semi-supervised learning in the era of foundation modelsCode1
Project-Probe-Aggregate: Efficient Fine-Tuning for Group Robustness—0
MoFE: Mixture of Frozen Experts Architecture—0
Lifelong Learning with Task-Specific Adaptation: Addressing the Stability-Plasticity Dilemma—0
Personalized Text Generation with Contrastive Activation Steering—0
LoRACode: LoRA Adapters for Code Embeddings—0
Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA—0
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space ModelsCode1
Addressing Overprescribing Challenges: Fine-Tuning Large Language Models for Medication Recommendation TasksCode0
PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level Adaptation—0
Re-Imagining Multimodal Instruction Tuning: A Representation ViewCode0
LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM—0
CLLoRA: An Approach to Measure the Effects of the Context Length for LLM Fine-Tuning—0
SECURA: Sigmoid-Enhanced CUR Decomposition with Uninterrupted Retention and Low-Rank Adaptation in Large Language Models—0
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization AlignmentCode2
ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models—0
R-LoRA: Random Initialization of Multi-Head LoRA for Multi-Task LearningCode1
Sparsity May Be All You Need: Sparse Random Parameter AdaptationCode0
R^3Mem: Bridging Memory Retention and Retrieval via Reversible Compression—0
Generative Modeling of Individual Behavior at Scale—0
Sculpting [CLS] Features for Pre-Trained Model-Based Class-Incremental Learning—0
LoRA-GGPO: Mitigating Double Descent in LoRA Fine-Tuning via Gradient-Guided Perturbation OptimizationCode0
NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language ModelsCode0
Black Sheep in the Herd: Playing with Spuriously Correlated Attributes for Vision-Language Recognition—0
Token Adaptation via Side Graph Convolution for Temporally and Spatially Efficient Fine-tuning of 3D Point Cloud TransformersCode0
LSR-Adapt: Ultra-Efficient Parameter Tuning with Matrix Low Separation Rank Kernel Adaptation—0
BeamLoRA: Beam-Constraint Low-Rank Adaptation—0
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuning—0
Revisiting Privacy, Utility, and Efficiency Trade-offs when Fine-Tuning Large Language Models—0
SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMsCode2
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRACode0
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent—0
FLAG-Trader: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading—0
CiteCheck: Towards Accurate Citation Faithfulness DetectionCode0
CoPEFT: Fast Adaptation Framework for Multi-Agent Collaborative Perception with Parameter-Efficient Fine-TuningCode1
Hallucinations and Truth: A Comprehensive Accuracy Evaluation of RAG, LoRA and DoRA—0
DiffoRA: Enabling Parameter-Efficient LLM Fine-Tuning via Differential Low-Rank Matrix Adaptation—0
Show:102550
← PrevPage 4 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