Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 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/argonne-lcf/llm-inference-bench
공식 코드LLM-Inference-Bench: Inference Benchmarking of Large Language Models on AI Accelerators
https://github.com/ariapoy/active-learning-benchmark
공식 코드Re-Benchmarking Pool-Based Active Learning for Binary Classification
https://github.com/arijitthegame/hybrid-sampling
공식 코드https://github.com/armagaan/gnn-x-bench
공식 코드https://github.com/armanfard-lab/ati-net
공식 코드https://github.com/arnaudimai/clip-guesswho
공식 코드https://github.com/arnaumarin/hdnn-artifactbrainstate
공식 코드Hopfield-Enhanced Deep Neural Networks for Artifact-Resilient Brain State Decoding
https://github.com/arnegevaert/benchmark-general-imaging
공식 코드https://github.com/arpan-kusari/graph-plane-extraction-simulation
공식 코드Graph-theoretical approach to robust 3D normal extraction of LiDAR data
https://github.com/arplaboratory/vg_ssl
공식 코드VG-SSL: Benchmarking Self-supervised Representation Learning Approaches for Visual Geo-localization
https://github.com/art-jang/signing-outside-the-studio
공식 코드https://github.com/artajmir3/empot
공식 코드https://github.com/artanic30/hoiclip
공식 코드HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models
https://github.com/arvin0313/mecoin-gfscil
공식 코드An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
https://github.com/aryamanarora/causalgym
공식 코드CausalGym: Benchmarking causal interpretability methods on linguistic tasks
https://github.com/aryan-at-ul/aics_2023_submission
공식 코드Connecting the Dots: Graph Neural Network Powered Ensemble and Classification of Medical Images
https://github.com/aryanasadianuoit/Distilling-Knowledge-via-Intermediate-Classifier-Heads-DIH-
공식 코드https://github.com/aryanasadianuoit/Distilling-Knowledge-via-Intermediate-Classifiers
공식 코드https://github.com/aryaxai/dlbacktrace
공식 코드DLBacktrace: A Model Agnostic Explainability for any Deep Learning Models
https://github.com/as641651/linearalgebra-awareness-benchmark
공식 코드Benchmarking the Linear Algebra Awareness of TensorFlow and PyTorch
https://github.com/asalmehradfar/lantern
공식 코드LANTERN: A Machine Learning Framework for Lipid Nanoparticle Transfection Efficiency Prediction
https://github.com/asappresearch/imitkd
공식 코드Autoregressive Knowledge Distillation through Imitation Learning
https://github.com/asappresearch/spoken-ner
공식 코드On the Use of External Data for Spoken Named Entity Recognition
https://github.com/asdvfghg/bearingpga-net
공식 코드https://github.com/ashikiut/defan
공식 코드DefAn: Definitive Answer Dataset for LLMs Hallucination Evaluation
https://github.com/ashishrana160796/rerrfact
공식 코드RerrFact: Reduced Evidence Retrieval Representations for Scientific Claim Verification
https://github.com/ashispati/dmelodies_benchmarking
공식 코드https://github.com/ashispati/dmelodies_dataset
공식 코드https://github.com/ask-berkeley/badger-sbdd
공식 코드General Binding Affinity Guidance for Diffusion Models in Structure-Based Drug Design
https://github.com/asmadotgh/neural_chat_web
공식 코드Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
https://github.com/aspuru-guzik-group/olympus
공식 코드Olympus: a benchmarking framework for noisy optimization and experiment planning
https://github.com/ast-fortiss-tum/perturbation-drive
공식 코드Benchmarking Image Perturbations for Testing Automated Driving Assistance Systems
https://github.com/astarakee/segrap2023
공식 코드https://github.com/astral-group/bdc_mitigation_assessment
공식 코드https://github.com/astrovision/.github
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.