Papers with Code 아카이브

parameter-efficient fine-tuning

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/optsuite/LOZO

공식 코드

Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures

https://github.com/osu-mlb/petl_vision

공식 코드

Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition

https://github.com/osu-mlb/vit_peft_vision

공식 코드

Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition

https://github.com/outsider565/lora-ga

공식 코드

LoRA-GA: Low-Rank Adaptation with Gradient Approximation

https://github.com/p3eft-iclr-2025/p3eft-iclr-2025

공식 코드

Label Privacy in Split Learning for Large Models with Parameter-Efficient Training

https://github.com/paragonlight/meteor-of-lora

공식 코드

MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models

https://github.com/penfever/tabpfn-pt

공식 코드

TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks

https://github.com/penfever/tunetables

공식 코드

TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks

https://github.com/pilancilab/Riemannian_Preconditioned_LoRA

공식 코드

Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models

https://github.com/pilancilab/spectral_adapter

공식 코드

Spectral Adapter: Fine-Tuning in Spectral Space

https://github.com/prateeky2806/compeft

공식 코드

ComPEFT: Compression for Communicating Parameter Efficient Updates via Sparsification and Quantization

https://github.com/predibase/lora_bakeoff

공식 코드

LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report

https://github.com/psunlpgroup/fish-dip

공식 코드

Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning

https://github.com/pumpkin-co/mtl-lora

공식 코드

MTL-LoRA: Low-Rank Adaptation for Multi-Task Learning

https://github.com/qingruzhang/adalora

공식 코드

AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

https://github.com/qualcomm-ai-research/lr-qat

공식 코드

Low-Rank Quantization-Aware Training for LLMs

https://github.com/quiil/benchmarkingpathologyfoundationmodels

공식 코드

Benchmarking Pathology Foundation Models: Adaptation Strategies and Scenarios

https://github.com/r-three/phatgoose

공식 코드

Learning to Route Among Specialized Experts for Zero-Shot Generalization

https://github.com/r-three/t-few

공식 코드

Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning

https://github.com/rabeehk/compacter

공식 코드

Compacter: Efficient Low-Rank Hypercomplex Adapter Layers

https://github.com/rabeehk/hyperformer

공식 코드

Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks

https://github.com/rachtsy/molex

공식 코드

MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling

https://github.com/raman1121/diffusion_memorization_hpo

공식 코드

MemControl: Mitigating Memorization in Diffusion Models via Automated Parameter Selection

https://github.com/rambodazimi/kd-lora

공식 코드

KD-LoRA: A Hybrid Approach to Efficient Fine-Tuning with LoRA and Knowledge Distillation

https://github.com/rezaakb/peft-vit

공식 코드

Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting

https://github.com/riiid/ppap

공식 코드

Towards Practical Plug-and-Play Diffusion Models

https://github.com/rl4m/med-peft

공식 코드

Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Models

https://github.com/roim1998/apt

공식 코드

APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference

https://github.com/rominaoji/german-language-adapter

공식 코드

How to Tune a Multilingual Encoder Model for Germanic Languages: A Study of PEFT, Full Fine-Tuning, and Language Adapters

https://github.com/rongpiking/customttt

공식 코드

CustomTTT: Motion and Appearance Customized Video Generation via Test-Time Training

https://github.com/rosa-paper/rosa

공식 코드

ROSA: Random Subspace Adaptation for Efficient Fine-Tuning

https://github.com/rushendra10/hate-speech-detection-and-target-identification-in-devanagari-languages

공식 코드

LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMs

https://github.com/s-lora/s-lora

공식 코드

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

https://github.com/saeednajafi/riff

공식 코드

RIFF: Learning to Rephrase Inputs for Few-shot Fine-tuning of Language Models

https://github.com/samin-mehdizadeh/llama-persian-adaptation

공식 코드

Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation

https://github.com/sannim3/predicitons_with_explanations

공식 코드

SPARSEFIT: Few-shot Prompting with Sparse Fine-tuning for Jointly Generating Predictions and Natural Language Explanations

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.