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/eternityyw/tram-benchmark

공식 코드

TRAM: Benchmarking Temporal Reasoning for Large Language Models

https://github.com/ethz-spylab/autoadvexbench

공식 코드

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses

https://github.com/etrulls/slurm-gcp

공식 코드

Image Matching across Wide Baselines: From Paper to Practice

https://github.com/evelyn0414/opera

공식 코드

Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking

https://github.com/event-ahu/coesot

공식 코드

Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline

https://github.com/event-ahu/eventvot_benchmark

공식 코드

Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline

https://github.com/event-ahu/medical_image_analysis

공식 코드

CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset

https://github.com/event-ahu/openpar

공식 코드

SNN-PAR: Energy Efficient Pedestrian Attribute Recognition via Spiking Neural Networks

https://github.com/event-ahu/slowfast_event_track

공식 코드

Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach

https://github.com/evolutionary-intelligence/pypop

공식 코드

PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization

https://github.com/evolvinglmms-lab/lmms-eval

공식 코드

LMMs-Eval: Reality Check on the Evaluation of Large Multimodal Models

https://github.com/evotestops/loglead

공식 코드

LogLead -- Fast and Integrated Log Loader, Enhancer, and Anomaly Detector

https://github.com/ewendawi/llamea-bo

공식 코드

LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms

https://github.com/exalearn/covid-drug-design

공식 코드

Benchmarking Deep Graph Generative Models for Optimizing New Drug Molecules for COVID-19

https://github.com/exathlonbenchmark/divad

공식 코드

Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domains

https://github.com/explainableml/general-knowledge-transfer

공식 코드

Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

https://github.com/exqrch/indonesiannmt

공식 코드

Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia

https://github.com/extrality/iclr_naca_dataset_v0

공식 코드

An extensible Benchmarking Graph-Mesh dataset for studying Steady-State Incompressible Navier-Stokes Equations

https://github.com/ezequieldlrosa/isles22

공식 코드

ISLES 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset

https://github.com/fabiopardo/tonic

공식 코드

Tonic: A Deep Reinforcement Learning Library for Fast Prototyping and Benchmarking

https://github.com/fabrice-rossi/outlier-anomaly-detection

공식 코드

Meta-survey on outlier and anomaly detection

https://github.com/facaraff/SOS

공식 코드

The importance of being constrained: dealing with infeasible solutions in Differential Evolution and beyond

https://github.com/facebookresearch/BLINK

공식 코드

Scalable Zero-shot Entity Linking with Dense Entity Retrieval

https://github.com/facebookresearch/Ego-Exo

공식 코드

Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos

https://github.com/facebookresearch/FiD

공식 코드

Distilling Knowledge from Reader to Retriever for Question Answering

https://github.com/facebookresearch/Multi-IF

공식 코드

Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following

https://github.com/facebookresearch/PLRC

공식 코드

Point-Level Region Contrast for Object Detection Pre-Training

https://github.com/facebookresearch/SentAugment

공식 코드

Self-training Improves Pre-training for Natural Language Understanding

https://github.com/facebookresearch/audiobox-aesthetics

공식 코드

Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Sound

https://github.com/facebookresearch/benchmarl

공식 코드

BenchMARL: Benchmarking Multi-Agent Reinforcement Learning

https://github.com/facebookresearch/detectron

공식 코드

Focal Loss for Dense Object Detection

https://github.com/facebookresearch/dig-in

공식 코드

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity

https://github.com/facebookresearch/dynabench

공식 코드

Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks

https://github.com/facebookresearch/egotom

공식 코드

EgoToM: Benchmarking Theory of Mind Reasoning from Egocentric Videos

https://github.com/facebookresearch/evalgim

공식 코드

EvalGIM: A Library for Evaluating Generative Image Models

https://github.com/facebookresearch/exploring_exploration

공식 코드

An Exploration of Embodied Visual Exploration

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