Papers with Code 아카이브

Knowledge Distillation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 2
평가표: 11
보존된 평가 기록: 90

Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.

코드

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

https://github.com/AlephZr/CE-GAN

공식 코드

Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation

https://github.com/AlexHeyman/LLMGraphColoring

공식 코드

Evaluating the Systematic Reasoning Abilities of Large Language Models through Graph Coloring

https://github.com/AlfredsLapkovskis/SmartVideoStream

공식 코드

Benchmarking Dynamic SLO Compliance in Distributed Computing Continuum Systems

https://github.com/AlfredsLapkovskis/VideoStreamEnv

공식 코드

Benchmarking Dynamic SLO Compliance in Distributed Computing Continuum Systems

https://github.com/AlgTUDelft/B-FELSA

공식 코드

Benchmarking Flexible Electric Loads Scheduling Algorithms under Market Price Uncertainty

https://github.com/AlgTUDelft/ExpensiveOptimBenchmark

공식 코드

EXPObench: Benchmarking Surrogate-based Optimisation Algorithms on Expensive Black-box Functions

https://github.com/Alibaba-NLP/MultilangStructureKD

공식 코드

Structure-Level Knowledge Distillation For Multilingual Sequence Labeling

https://github.com/Alibaba-NLP/StructuralKD

공식 코드

Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor

https://github.com/Amazingren/AnyIR

공식 코드

Restore Anything Model via Efficient Degradation Adaptation

https://github.com/AmiiThinks/mon_mdp_neurips24

공식 코드

Beyond Optimism: Exploration With Partially Observable Rewards

https://github.com/Andrews2017/KINNEWS-and-KIRNEWS-Corpus

공식 코드

KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi

https://github.com/Andrewwango/deepinv-selfsup-fastmri

공식 코드

Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstruction

https://github.com/Antonio-Dee/tasi-testdata

공식 코드

Integrating Large Language Models and Knowledge Graphs for Extraction and Validation of Textual Test Data

https://github.com/ApocalypseH/EGMS

공식 코드

Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization

https://github.com/ArchipLab-LinfengZhang/pytorch-scalable-neural-networks

공식 코드

SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models

https://github.com/Ariya12138/CORAL

공식 코드

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation

https://github.com/Artanisax/Six-CD

공식 코드

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models

https://github.com/Ashigarg123/ShiftySpeech

공식 코드

ShiftySpeech: A Large-Scale Synthetic Speech Dataset with Distribution Shifts

https://github.com/AutodeskAILab/RobustPointSet

공식 코드

RobustPointSet: A Dataset for Benchmarking Robustness of Point Cloud Classifiers

https://github.com/Axeln78/Transferability-of-spectral-gnns

공식 코드

An Experimental Study of the Transferability of Spectral Graph Networks

https://github.com/BUPT-GAMMA/CPF

공식 코드

Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework

https://github.com/Babelscape/LLM-Oasis

공식 코드

Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis

https://github.com/Bala93/KD-MRI

공식 코드

KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow

https://github.com/BaranziniLab/KG_RAG

공식 코드

Biomedical knowledge graph-optimized prompt generation for large language models

https://github.com/Basvanstein/LearningFromNAS

공식 코드

Neural Network Design: Learning from Neural Architecture Search

https://github.com/BensonRen/BDIMNNA

공식 코드

Benchmarking deep inverse models over time, and the neural-adjoint method

https://github.com/BerserkerMother/Video-Summarization

공식 코드

SELF-VS: Self-supervised Encoding Learning For Video Summarization

https://github.com/BhuvanSaravanan/power_transformer_fault_detection

공식 코드

Benchmarking Traditional Machine Learning and Deep Learning Models for Fault Detection in Power Transformers

https://github.com/BililiCode/ARGD

공식 코드

Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation

https://github.com/BinWang28/AnomalyHop

공식 코드

AnomalyHop: An SSL-based Image Anomaly Localization Method

https://github.com/BlaiseMuhirwa/flatnav

공식 코드

Down with the Hierarchy: The 'H' in HNSW Stands for "Hubs"

https://github.com/Boazrciasn/Quaternion-Capsule-Networks

공식 코드

Quaternion Capsule Networks

https://github.com/BradSegal/ClinicalDataSimulator

공식 코드

Bridging the Generalisation Gap: Synthetic Data Generation for Multi-Site Clinical Model Validation

https://github.com/BrightBlueCheese/transformers_and_chemistry

공식 코드

The Role of Model Architecture and Scale in Predicting Molecular Properties: Insights from Fine-Tuning RoBERTa, BART, and LLaMA

https://github.com/CAMMA-public/ORPose-color

공식 코드

Self-supervision on Unlabelled OR Data for Multi-person 2D/3D Human Pose Estimation

https://github.com/CAMMA-public/cholect45

공식 코드

Data Splits and Metrics for Method Benchmarking on Surgical Action Triplet Datasets

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