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/myflashbarry/LLM-benchmarking
공식 코드Exploring Graph Tasks with Pure LLMs: A Comprehensive Benchmark and Investigation
https://github.com/mzhaoshuai/slimclr
공식 코드https://github.com/mzhenz/lgd
공식 코드Lightweight Model Pre-training via Language Guided Knowledge Distillation
https://github.com/n3il666/meta-dmoe
공식 코드Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts
https://github.com/naamiinepal/tunevlseg
공식 코드TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Models
https://github.com/nabenabe0928/mfhpo-simulator
공식 코드Fast Benchmarking of Asynchronous Multi-Fidelity Optimization on Zero-Cost Benchmarks
https://github.com/nabenabe0928/mfhpo-simulator-experiments
공식 코드Fast Benchmarking of Asynchronous Multi-Fidelity Optimization on Zero-Cost Benchmarks
https://github.com/nabja/isimed
공식 코드https://github.com/nagejacob/tbsn
공식 코드Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising
https://github.com/nakulrampal/retchemqa
공식 코드Single and Multi-Hop Question-Answering Datasets for Reticular Chemistry with GPT-4-Turbo
https://github.com/name-is-what/nc2d
공식 코드https://github.com/namespace-pt/adon
공식 코드Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval
https://github.com/namisan/mt-dnn
공식 코드https://github.com/namkoong-lab/qgym
공식 코드QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
https://github.com/nano-neuro-research-lab/machine-learning-cryptanalysis-of-a-quantum-random-number-generator
공식 코드Machine Learning Cryptanalysis of a Quantum Random Number Generator
https://github.com/nanpengyu/pmubage
공식 코드https://github.com/narabzad/llm-relevance-judgement-comparison
공식 코드https://github.com/natashamjaques/neural_chat
공식 코드Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems
https://github.com/nathanaelbosch/capos
공식 코드https://github.com/nathangavenski/il-datasets
공식 코드Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking
https://github.com/naufalso/cityscape-adverse
공식 코드https://github.com/naver/bergen
공식 코드BERGEN: A Benchmarking Library for Retrieval-Augmented Generation
https://github.com/naver/kapture-localization
공식 코드https://github.com/naver/multilingual-distilwhisper
공식 코드https://github.com/naver/splade
공식 코드Benchmarking Middle-Trained Language Models for Neural Search
https://github.com/nayeemrizve/invariance-equivariance
공식 코드Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning
https://github.com/ncbi-nlp/BLUE_Benchmark
공식 코드https://github.com/ncbi-nlp/BioSentVec
공식 코드BioSentVec: creating sentence embeddings for biomedical texts
https://github.com/ncbi-nlp/BioWordVec
공식 코드BioSentVec: creating sentence embeddings for biomedical texts
https://github.com/ncbi-nlp/NCBI_BERT
공식 코드https://github.com/ncbi-nlp/NegBio
공식 코드NegBio: a high-performance tool for negation and uncertainty detection in radiology reports
https://github.com/ncbi-nlp/bioredirect
공식 코드Enhancing Biomedical Relation Extraction with Directionality
https://github.com/ncbi/speciesassignment
공식 코드Assigning Species Information to Corresponding Genes by a Sequence Labeling Framework
https://github.com/ncclabsustech/ifcis-55
공식 코드Immunofluorescence Capillary Imaging Segmentation: Cases Study
https://github.com/ncsoft/Align-to-Distill
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.