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 751–800 of 935 papers

TitleStatusHype
LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM—0
LoRTA: Low Rank Tensor Adaptation of Large Language Models—0
LoTR: Low Tensor Rank Weight Adaptation—0
LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits—0
Low-Rank Adaptation of Neural Fields—0
Low-Rank Adapters Meet Neural Architecture Search for LLM Compression—0
Low-rank Attention Side-Tuning for Parameter-Efficient Fine-Tuning—0
LPT++: Efficient Training on Mixture of Long-tailed Experts—0
LSR-Adapt: Ultra-Efficient Parameter Tuning with Matrix Low Separation Rank Kernel Adaptation—0
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning—0
Mamba State-Space Models Are Lyapunov-Stable Learners—0
MAP: Revisiting Weight Decomposition for Low-Rank Adaptation—0
Adapters Mixup: Mixing Parameter-Efficient Adapters to Enhance the Adversarial Robustness of Fine-tuned Pre-trained Text Classifiers—0
MAST-Pro: Dynamic Mixture-of-Experts for Adaptive Segmentation of Pan-Tumors with Knowledge-Driven Prompts—0
Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences—0
Matrix-Transformation Based Low-Rank Adaptation (MTLoRA): A Brain-Inspired Method for Parameter-Efficient Fine-Tuning—0
MedFocusCLIP : Improving few shot classification in medical datasets using pixel wise attention—0
Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization—0
MergeRepair: An Exploratory Study on Merging Task-Specific Adapters in Code LLMs for Automated Program Repair—0
Meta-Adapter: Parameter Efficient Few-Shot Learning through Meta-Learning—0
Meta-Learning Adaptable Foundation Models—0
Meta-Learning Hyperparameters for Parameter Efficient Fine-Tuning—0
MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning—0
MetaTT: A Global Tensor-Train Adapter for Parameter-Efficient Fine-Tuning—0
MiLoRA: Efficient Mixture of Low-Rank Adaptation for Large Language Models Fine-tuning—0
MIP: CLIP-based Image Reconstruction from PEFT Gradients—0
MIRA: A Method of Federated MultI-Task Learning for LaRge LAnguage Models—0
Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models—0
Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning—0
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent—0
Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models—0
Mixture of Physical Priors Adapter for Parameter-Efficient Fine-Tuning—0
Mixture of Routers—0
Model Diffusion for Certifiable Few-shot Transfer Learning—0
MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models—0
MoFE: Mixture of Frozen Experts Architecture—0
MoLoRec: A Generalizable and Efficient Framework for LLM-Based Recommendation—0
MoPEFT: A Mixture-of-PEFTs for the Segment Anything Model—0
Multi-Head Adapter Routing for Cross-Task Generalization—0
MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition—0
Inducing Generalization across Languages and Tasks using Featurized Low-Rank Mixtures—0
Navigating Uncertainty: Optimizing API Dependency for Hallucination Reduction in Closed-Book Question Answering—0
NEAT: Nonlinear Parameter-efficient Adaptation of Pre-trained Models—0
Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models—0
NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation—0
Noise-Robustness Through Noise: Asymmetric LoRA Adaption with Poisoning Expert—0
Non-Intrusive Adaptation: Input-Centric Parameter-efficient Fine-Tuning for Versatile Multimodal Modeling—0
NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models—0
Norm-Bounded Low-Rank Adaptation—0
Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models—0
Show:102550
← PrevPage 16 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