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/bytedance/MTVQA

공식 코드

MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering

https://github.com/bytedance/pargo

공식 코드

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

https://github.com/bzantium/bert-AAD

공식 코드

Knowledge Distillation for BERT Unsupervised Domain Adaptation

https://github.com/c2dc/t800

공식 코드

Design and implementation of intelligent packet filtering in IoT microcontroller-based devices

https://github.com/cadurosar/graph_kd

공식 코드

Deep geometric knowledge distillation with graphs

https://github.com/caiyun-ai/gar

공식 코드

Benchmarking and Understanding Compositional Relational Reasoning of LLMs

https://github.com/caiyuxuan1120/daf

공식 코드

A Discrepancy Aware Framework for Robust Anomaly Detection

https://github.com/caizhongang/SMPLer-X

공식 코드

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

https://github.com/calvin-zcx/scehr

공식 코드

SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records

https://github.com/calvintanama/qd-driver-activity-reco

공식 코드

Quantized Distillation: Optimizing Driver Activity Recognition Models for Resource-Constrained Environments

https://github.com/cambridgeltl/sapbert

공식 코드

Self-Alignment Pretraining for Biomedical Entity Representations

https://github.com/camma-public/attention-tripnet

공식 코드

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

https://github.com/camma-public/ivtmetrics

공식 코드

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

https://github.com/camma-public/tripnet

공식 코드

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

https://github.com/canjiali/PARADE

공식 코드

PARADE: Passage Representation Aggregation for Document Reranking

https://github.com/cantbebetter2/rdd

공식 코드

Relational Diffusion Distillation for Efficient Image Generation

https://github.com/cap-ntu/FedReID

공식 코드

Optimizing Performance of Federated Person Re-identification: Benchmarking and Analysis

https://github.com/caperock/robustai

공식 코드

Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation

https://github.com/capoe/benchml

공식 코드

BenchML: an extensible pipelining framework for benchmarking representations of materials and molecules at scale

https://github.com/cardio-ai/cadp

공식 코드

Content-Aware Differential Privacy with Conditional Invertible Neural Networks

https://github.com/cardwing/Codes-for-IntRA-KD

공식 코드

Inter-Region Affinity Distillation for Road Marking Segmentation

https://github.com/cardwing/Codes-for-Lane-Detection

공식 코드

Learning Lightweight Lane Detection CNNs by Self Attention Distillation

https://github.com/carkham/fedsd2c

공식 코드

One-shot Federated Learning via Synthetic Distiller-Distillate Communication

https://github.com/carlomarxdk/trilemma-of-truth

공식 코드

The Trilemma of Truth in Large Language Models

https://github.com/caroladoerr/leadingonedac

공식 코드

Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration

https://github.com/carrenD/ummkd

공식 코드

Unpaired Multi-modal Segmentation via Knowledge Distillation

https://github.com/cartucho/surgt_benchmarking

공식 코드

SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery

https://github.com/castorini/dhr

공식 코드

Aggretriever: A Simple Approach to Aggregate Textual Representations for Robust Dense Passage Retrieval

https://github.com/castorini/ragnarok

공식 코드

Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track

https://github.com/cathyxl/magic

공식 코드

MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration

https://github.com/causalens/cdml-neurips2020

공식 코드

Data Generating Process to Evaluate Causal Discovery Techniques for Time Series Data

https://github.com/cavalab/ecg-survival-benchmark

공식 코드

A Closer Look at Mortality Risk Prediction from Electrocardiograms

https://github.com/cbaziotis/lm-prior-for-nmt

공식 코드

Language Model Prior for Low-Resource Neural Machine Translation

https://github.com/cbg-ethz/bmi

공식 코드

Beyond Normal: On the Evaluation of Mutual Information Estimators

https://github.com/cbg-ethz/subgroupseparation

공식 코드

High-Dimensional Inference in Bayesian Networks

https://github.com/ccasimiro88/self-distillation-gxlt-qa

공식 코드

Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge Distillation

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