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/geometric-intelligence/TopoBench
공식 코드TopoBench: A Framework for Benchmarking Topological Deep Learning
https://github.com/geondopark/ckd
공식 코드Distilling Linguistic Context for Language Model Compression
https://github.com/geonhobang/RadarDistill
공식 코드https://github.com/georg-wolflein/histaug
공식 코드Benchmarking Pathology Feature Extractors for Whole Slide Image Classification
https://github.com/gersteinlab/medagents-benchmark
공식 코드MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
https://github.com/gestaltcogteam/basicts
공식 코드https://github.com/gewu-lab/cross-modal-distillation
공식 코드Robust Cross-Modal Knowledge Distillation for Unconstrained Videos
https://github.com/geyuying/PF-AFN
공식 코드https://github.com/gfnorg/gfn-diffusion
공식 코드https://github.com/ggjy/DeFeat.pytorch
공식 코드https://github.com/ggjy/vision_weak_to_strong
공식 코드Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
https://github.com/gglab-ku/turkish-plu
공식 코드Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish
https://github.com/ghrua/seqpe
공식 코드https://github.com/ghwang-s/abkd
공식 코드https://github.com/giakoumoglou/distillers
공식 코드https://github.com/giarcieri/assessing-the-influence-of-models-on-the-performance-of-reinforcement-learning-algorithms
공식 코드https://github.com/gidecarlo/vitagraph
공식 코드VitaGraph: Building a Knowledge Graph for Biologically Relevant Learning Tasks
https://github.com/gideonfr/emprox
공식 코드EmProx: Neural Network Performance Estimation For Neural Architecture Search
https://github.com/giganticode/throwbench
공식 코드ThrowBench: Benchmarking LLMs by Predicting Runtime Exceptions
https://github.com/gilesluo/dtr-bench
공식 코드https://github.com/giovannicatalani/mario
공식 코드Towards scalable surrogate models based on Neural Fields for large scale aerodynamic simulations
https://github.com/giovannimen/cpcad-bench
공식 코드CIPCaD-Bench: Continuous Industrial Process datasets for benchmarking Causal Discovery methods
https://github.com/gist-ailab/teaching-where-to-look
공식 코드https://github.com/gistairc/HS-SOD
공식 코드Hyperspectral Image Dataset for Benchmarking on Salient Object Detection
https://github.com/git-disl/EnsembleBench
공식 코드Promoting High Diversity Ensemble Learning with EnsembleBench
https://github.com/git-disl/LRBench
공식 코드Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks
https://github.com/github-usr-ano/temporal_graph_data_pdes
공식 코드Synthetic Datasets for Machine Learning on Spatio-Temporal Graphs using PDEs
https://github.com/giu-guarino/rho-pnn
공식 코드Zero-Shot Hyperspectral Pansharpening Using Hysteresis-Based Tuning for Spectral Quality Control
https://github.com/gizi1/NormKD
공식 코드https://github.com/gjorgjinac/dynamorep_problem_classification
공식 코드https://github.com/gklmip/cl-xabsa
공식 코드CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis
https://github.com/glam-imperial/AudioXgen
공식 코드Audio Explanation Synthesis with Generative Foundation Models
https://github.com/globalflownet/globalflownet
공식 코드GlobalFlowNet: Video Stabilization using Deep Distilled Global Motion Estimates
https://github.com/globosco/A-learned-sorted-table-search-library
공식 코드Learned Sorted Table Search and Static Indexes in Small Model Space
https://github.com/globosco/A-modified-SOSD-platform-for-benchmarking-Branchy-vs-Branch-free-search-algorithms
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.