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/jongwooko/distillm-2
DistiLLM: Towards Streamlined Distillation for Large Language Models
https://github.com/jorisvandenbossche/target-encoder-benchmarks
https://github.com/josepatino/Voice-Privacy-Challenge-2020
https://github.com/josephkj/eli
https://github.com/jpmcd/TensorFlow-KnowledgeDistillation
https://github.com/js-aguiar/wheat-object-detection
https://github.com/jsong0327/HumanDetectionServer
https://github.com/jsrdcht/SSL-Backdoor
https://github.com/judge0/judge0
ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?
https://github.com/juergenlandauer/Maya-Challenge
https://github.com/jugg1er/air
https://github.com/jwwangchn/mmdet-aitod
https://github.com/jxbz/signSGD
signSGD with Majority Vote is Communication Efficient And Fault Tolerant
https://github.com/jzlei/scEntropy
Single-cell entropy to quantify the cellular transcription from single-cell RNA-seq data
https://github.com/kaiko-ai/eva
Benchmarking Self-Supervised Learning on Diverse Pathology Datasets
https://github.com/kaistAI/LangBridge
Orca: Progressive Learning from Complex Explanation Traces of GPT-4
https://github.com/kakaobrain/honeybee
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
https://github.com/kalelpark/ral
https://github.com/kangmintong/c-rag
Learning to Retrieve In-Context Examples for Large Language Models
https://github.com/karan96/NewOne
https://github.com/kaung-htet-myat/Multi-teachers-Knowledge-Distillation
https://github.com/kaung-htet-myat/feature-distillation-tf
https://github.com/kaushal-py/seg-degan
Data-free Knowledge Distillation for Segmentation using Data-Enriching GAN
https://github.com/kaushikb258/Habitat_RL
https://github.com/kawshik8/DL-project
https://github.com/kcorder/qmix_variants
https://github.com/kenjyoung/MinAtar
The Arcade Learning Environment: An Evaluation Platform for General Agents
https://github.com/keonlee9420/Comprehensive-E2E-TTS
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/Comprehensive-Transformer-TTS
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/DiffSinger
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/Expressive-FastSpeech2
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/PortaSpeech
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/STYLER
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/keonlee9420/StyleSpeech
FastSpeech 2: Fast and High-Quality End-to-End Text to Speech
https://github.com/khaled2ahmed/k2a
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.