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/prgumd/PRGFlow

공식 코드

PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry

https://github.com/primeqa/primeqa

공식 코드

Learning Cross-Lingual IR from an English Retriever

https://github.com/princeton-nlp/intercode

공식 코드

InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback

https://github.com/princeton-vl/SpatialSense

공식 코드

SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition

https://github.com/princetonvisualai/imagecaptioning-bias

공식 코드

Understanding and Evaluating Racial Biases in Image Captioning

https://github.com/princetonvisualai/intersectionality

공식 코드

Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation

https://github.com/pris-cv/pascal-ea

공식 코드

Benchmarking Segmentation Models with Mask-Preserved Attribute Editing

https://github.com/pritamqu/XKD

공식 코드

XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning

https://github.com/profjsb/deepCR

공식 코드

deepCR: Cosmic Ray Rejection with Deep Learning

https://github.com/profyliu/bsnsing

공식 코드

bsnsing: A decision tree induction method based on recursive optimal boolean rule composition

https://github.com/programmablebio/pepmlm

공식 코드

PepMLM: Target Sequence-Conditioned Generation of Therapeutic Peptide Binders via Span Masked Language Modeling

https://github.com/proroklab/popgym

공식 코드

POPGym: Benchmarking Partially Observable Reinforcement Learning

https://github.com/proroklab/vectorizedmultiagentsimulator

공식 코드

VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning

https://github.com/pty72/rlkd

공식 코드

Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment

https://github.com/pudumagico/kr2024

공식 코드

Declarative Knowledge Distillation from Large Language Models for Visual Question Answering Datasets

https://github.com/pulkit-khandelwal/upenn-picsl-brain-ex-vivo

공식 코드

Automated deep learning segmentation of high-resolution 7 T postmortem MRI for quantitative analysis of structure-pathology correlations in neurodegenerative diseases

https://github.com/pulse-ml/momfbo-algorithm

공식 코드

Leveraging Trust for Joint Multi-Objective and Multi-Fidelity Optimization

https://github.com/puredefence/advbench4text

공식 코드

Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks

https://github.com/puzzle-ai/unpuzzle

공식 코드

UnPuzzle: A Unified Framework for Pathology Image Analysis

https://github.com/pxaris/fm-music-tagging

공식 코드

Universal Music Representations? Evaluating Foundation Models on World Music Corpora

https://github.com/pxaris/lc-protonets

공식 코드

Universal Music Representations? Evaluating Foundation Models on World Music Corpora

https://github.com/pxiangwu/forb

공식 코드

FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding

https://github.com/pyf98/dphubert

공식 코드

DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models

https://github.com/pygda-team/pygda

공식 코드

Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation

https://github.com/pygod-team/pygod

공식 코드

BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs

https://github.com/pyjulie/medical-vlms-ood-detection

공식 코드

Delving into Out-of-Distribution Detection with Medical Vision-Language Models

https://github.com/pyjulie/monica

공식 코드

MONICA: Benchmarking on Long-tailed Medical Image Classification

https://github.com/pykeen/benchmarking

공식 코드

Bringing Light Into the Dark: A Large-scale Evaluation of Knowledge Graph Embedding Models Under a Unified Framework

https://github.com/pykeen/pykeen

공식 코드

A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs

https://github.com/pykeen/ranking-metrics-manuscript

공식 코드

A Unified Framework for Rank-based Evaluation Metrics for Link Prediction in Knowledge Graphs

https://github.com/pyt-team/TopoBenchmarkX

공식 코드

TopoBench: A Framework for Benchmarking Topological Deep Learning

https://github.com/pytorch/benchmark

공식 코드

TorchBench: Benchmarking PyTorch with High API Surface Coverage

https://github.com/qbetterk/VarBench

공식 코드

VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation

https://github.com/qcraftai/distill-bev

공식 코드

DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation

https://github.com/qcri/llmebench

공식 코드

LLMeBench: A Flexible Framework for Accelerating LLMs Benchmarking

https://github.com/qhuni/deve-qa

공식 코드

Question-Answering Dense Video Events

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