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/yale-nlp/metafaith
공식 코드MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs
https://github.com/yan-gao-GY/Muti-teacherKD
공식 코드https://github.com/yanbeic/CCL
공식 코드Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
https://github.com/yandex-research/adaptive-diffusion
공식 코드https://github.com/yangheng95/OmniGenomeBench
공식 코드OmniGenBench: Automating Large-scale in-silico Benchmarking for Genomic Foundation Models
https://github.com/yangheng95/omnigenbench
공식 코드OmniGenBench: A Modular Platform for Reproducible Genomic Foundation Models Benchmarking
https://github.com/yangling0818/vqgraph
공식 코드VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
https://github.com/yangliuy/NeuralResponseRanking
공식 코드https://github.com/yanguojun123/medical-dialogue
공식 코드ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
https://github.com/yangyeeee/apsnet
공식 코드https://github.com/yangyifei729/laco
공식 코드https://github.com/yangzhch6/ReSocratic
공식 코드OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling
https://github.com/yanx27/2dpass
공식 코드2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
https://github.com/yanzhuguo/llm-diversity
공식 코드https://github.com/yaochie/multimodal-baselines
공식 코드Strong and Simple Baselines for Multimodal Utterance Embeddings
https://github.com/yaolu-zjut/Navigation-LLM-layer-pruning
공식 코드https://github.com/yaoming95/ciat
공식 코드Counter-Interference Adapter for Multilingual Machine Translation
https://github.com/yaoxufeng/rtlrewriter-bench
공식 코드RTLRewriter: Methodologies for Large Models aided RTL Code Optimization
https://github.com/yaoyao-liu/online-hyperparameter-optimization
공식 코드Online Hyperparameter Optimization for Class-Incremental Learning
https://github.com/yaoyu-33/quantum_dynamics_machine_learning
공식 코드Emulating Quantum Dynamics with Neural Networks via Knowledge Distillation
https://github.com/yaozzz666/dscf-sr
공식 코드Distillation-Supervised Convolutional Low-Rank Adaptation for Efficient Image Super-Resolution
https://github.com/yazdanimehdi/fragxsitedti
공식 코드https://github.com/ybai-nlp/edubench
공식 코드https://github.com/yccm/ega
공식 코드Distilling Knowledge from Self-Supervised Teacher by Embedding Graph Alignment
https://github.com/ycfu/BubGAN
공식 코드BubGAN: Bubble Generative Adversarial Networks for Synthesizing Realistic Bubbly Flow Images
https://github.com/ychtanaka/marine-snow
공식 코드https://github.com/yczhou001/longbench-t2i
공식 코드https://github.com/yegyu-han/senseshift6d
공식 코드https://github.com/yehias21/vrp-benchmarks
공식 코드SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem
https://github.com/yellow07200/ESD_labeling_tool
공식 코드A Neuromorphic Dataset for Object Segmentation in Indoor Cluttered Environment
https://github.com/yellowmessenger/ood-detection
공식 코드BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection
https://github.com/yellowpancake/tcil
공식 코드Resolving Task Confusion in Dynamic Expansion Architectures for Class Incremental Learning
https://github.com/yellowtownhz/IE-KD
공식 코드Revisiting Knowledge Distillation: An Inheritance and Exploration Framework
https://github.com/yeongseoj/conkd
공식 코드https://github.com/yerevann/mimic3-benchmarks
공식 코드Multitask learning and benchmarking with clinical time series data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.