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/ecker-lab/sensorium_2023

공식 코드

Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos

https://github.com/eclipsess/awesome-efficient-reasoning-llms

공식 코드

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

https://github.com/ecnu-text-computing/knowledge-editing-benchmark

공식 코드

Benchmarking and Rethinking Knowledge Editing for Large Language Models

https://github.com/eddardd/tep-domain-adaptation

공식 코드

Benchmarking Domain Adaptation for Chemical Processes on the Tennessee Eastman Process

https://github.com/eden500/Noisy-Labels-Instance-Segmentation

공식 코드

Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters

https://github.com/edinburghnlp/aces

공식 코드

Machine Translation Meta Evaluation through Translation Accuracy Challenge Sets

https://github.com/edinburghnlp/mmlongbench

공식 코드

MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly

https://github.com/edisonleeeee/lrgae

공식 코드

Revisiting and Benchmarking Graph Autoencoders: A Contrastive Learning Perspective

https://github.com/edocanonymous/ks-detr

공식 코드

KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer

https://github.com/edornd/contrastive-distillation

공식 코드

A Contrastive Distillation Approach for Incremental Semantic Segmentation in Aerial Images

https://github.com/eduardacaldeira/compression_bias_survey

공식 코드

Model Compression Techniques in Biometrics Applications: A Survey

https://github.com/eduardacaldeira/mst-kd

공식 코드

MST-KD: Multiple Specialized Teachers Knowledge Distillation for Fair Face Recognition

https://github.com/edwardyu/soft-evidence-bnn

공식 코드

Bayesian Neural Networks with Soft Evidence

https://github.com/efeslab/consumerbench

공식 코드

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices

https://github.com/efficienttraining/labelbench

공식 코드

LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning

https://github.com/ehsansaleh/btspinn

공식 코드

Learning from Integral Losses in Physics Informed Neural Networks

https://github.com/ej0cl6/textee

공식 코드

TextEE: Benchmark, Reevaluation, Reflections, and Future Challenges in Event Extraction

https://github.com/ekansh09/lrh-net

공식 코드

LRH-Net: A Multi-Level Knowledge Distillation Approach for Low-Resource Heart Network

https://github.com/elasticdeeplearning/edl

공식 코드

Large-scale Knowledge Distillation with Elastic Heterogeneous Computing Resources

https://github.com/elcronos/Defense-Friendly

공식 코드

Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty

https://github.com/elenamer/noisebench

공식 코드

NoiseBench: Benchmarking the Impact of Real Label Noise on Named Entity Recognition

https://github.com/eleonorapoeta/benchmarking-kan

공식 코드

A Benchmarking Study of Kolmogorov-Arnold Networks on Tabular Data

https://github.com/elgazzarr/fmri-gnns

공식 코드

Benchmarking Graph Neural Networks for FMRI analysis

https://github.com/elgazzarr/fmri-s4

공식 코드

fMRI-S4: learning short- and long-range dynamic fMRI dependencies using 1D Convolutions and State Space Models

https://github.com/eliasbenussi/nn-cert-individual-fairness

공식 코드

Individual Fairness Guarantees for Neural Networks

https://github.com/elki-project/elki

공식 코드

ELKI: A large open-source library for data analysis - ELKI Release 0.7.5 "Heidelberg"

https://github.com/elliottyan/gpt_versus_mt_experts

공식 코드

Benchmarking GPT-4 against Human Translators: A Comprehensive Evaluation Across Languages, Domains, and Expertise Levels

https://github.com/elseviersoftwarex/softx-d-22-00288

공식 코드

A framework for benchmarking clustering algorithms

https://github.com/elu-lab/mart

공식 코드

Leveraging Large Language Models for Active Merchant Non-player Characters

https://github.com/elvishelvis/lca-on-the-line

공식 코드

LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies

https://github.com/elwer/perf_dd

공식 코드

Towards Computational Performance Engineering for Unsupervised Concept Drift Detection -- Complexities, Benchmarking, Performance Analysis

https://github.com/emadeldeen24/adatime

공식 코드

ADATIME: A Benchmarking Suite for Domain Adaptation on Time Series Data

https://github.com/emannix/tintem-teacher-in-the-middle

공식 코드

Faithful Label-free Knowledge Distillation

https://github.com/emanuelevivoli/cdf

공식 코드

Comics Datasets Framework: Mix of Comics datasets for detection benchmarking

https://github.com/emb-ai/rclicks

공식 코드

RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation

https://github.com/embeddings-benchmark/mteb

공식 코드

MTEB: Massive Text Embedding Benchmark

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