Papers with Code 아카이브
parameter-efficient fine-tuning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 10
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Gated Integration of Low-Rank Adaptation for Continual Learning of Language Models
AdUE: Improving uncertainty estimation head for LoRA adapters in LLMs
CoLA: Collaborative Low-Rank Adaptation
VP Lab: a PEFT-Enabled Visual Prompting Laboratory for Semantic Segmentation
4,500 Seconds: Small Data Training Approaches for Deep UAV Audio Classification
15,500 Seconds: Lean UAV Classification Leveraging PEFT and Pre-Trained Networks
ABBA: Highly Expressive Hadamard Product Adaptation for Large Language Models
OSoRA: Output-Dimension and Singular-Value Initialized Low-Rank Adaptation
Dual Decomposition of Weights and Singular Value Low Rank Adaptation
Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability Hypothesis
Privacy Preserving Conversion Modeling in Data Clean Room
Efficient Federated Class-Incremental Learning of Pre-Trained Models via Task-agnostic Low-rank Residual Adaptation
SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization
Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection
Parameter Efficient Continual Learning with Dynamic Low-Rank Adaptation
Memory-Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation
Reasoning on a Budget: Miniaturizing DeepSeek R1 with SFT-GRPO Alignment for Instruction-Tuned LLMs
Multi-Token Prediction Needs Registers
PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning
Parameter-Efficient Fine-Tuning of Vision Foundation Model for Forest Floor Segmentation from UAV Imagery
DAPE: Dual-Stage Parameter-Efficient Fine-Tuning for Consistent Video Editing with Diffusion Models
Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas
Efficient Telecom Specific LLM: TSLAM-Mini with QLoRA and Digital Twin Data
Leveraging Large Language Models for enzymatic reaction prediction and characterization
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
Vision Graph Prompting via Semantic Low-Rank Decomposition
On-Device LLM for Context-Aware Wi-Fi Roaming
Deepfakes on Demand: the rise of accessible non-consensual deepfake image generators
HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models
Federated Adapter on Foundation Models: An Out-Of-Distribution Approach
SpectrumFM: A Foundation Model for Intelligent Spectrum Management
AdCare-VLM: Leveraging Large Vision Language Model (LVLM) to Monitor Long-Term Medication Adherence and Care
Vision-Language Model-Based Semantic-Guided Imaging Biomarker for Early Lung Cancer Detection
DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images
NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.