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/Saumajit/BanglaNLP/tree/main/Task_2
공식 코드https://github.com/Saurabhbhati/DASS
공식 코드DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners
https://github.com/SaverioVad/HAD_Net
공식 코드https://github.com/Sean-Bin-Yang/LightPath
공식 코드LightPath: Lightweight and Scalable Path Representation Learning
https://github.com/Seanseattle/MobileFaceSwap
공식 코드MobileFaceSwap: A Lightweight Framework for Video Face Swapping
https://github.com/Seed3D/Dora
공식 코드Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders
https://github.com/SeongKu-Kang/DE-RRD_CIKM20
공식 코드DE-RRD: A Knowledge Distillation Framework for Recommender System
https://github.com/ServiceNow/repliqa
공식 코드RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
https://github.com/SewoongLab/FLIP
공식 코드https://github.com/SforAiDl/KD_Lib
공식 코드KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and Quantization
https://github.com/ShambhaviCodes/CLIPOT
공식 코드Words Matter: Leveraging Individual Text Embeddings for Code Generation in CLIP Test-Time Adaptation
https://github.com/ShaohuaDong2021/LoReTrack
공식 코드LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
https://github.com/ShawnXYang/Face-Robustness-Benchmark
공식 코드RobFR: Benchmarking Adversarial Robustness on Face Recognition
https://github.com/SimonLupart/disco-conv-splade
공식 코드DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search
https://github.com/SimonThomine/CSE
공식 코드CSE: Surface Anomaly Detection with Contrastively Selected Embedding
https://github.com/SimonThomine/DBFAD
공식 코드https://github.com/SimonThomine/MixedTeacher
공식 코드MixedTeacher : Knowledge Distillation for fast inference textural anomaly detection
https://github.com/Simonlee711/FEET
공식 코드https://github.com/SirRob1997/Descending-through-a-Crowded-Valley---Results
공식 코드Descending through a Crowded Valley - Benchmarking Deep Learning Optimizers
https://github.com/SongBaiHust/Adversarial_Metric_Attack
공식 코드Adversarial Metric Attack and Defense for Person Re-identification
https://github.com/SonyResearch/IDEAL
공식 코드IDEAL: Query-Efficient Data-Free Learning from Black-box Models
https://github.com/Soumyabrata/HDR-cloud-segmentation
공식 코드https://github.com/Spiegeldondi/A-Hybrid-Quantum-Classical-Framework-for-Reinforcement-Learning-of-Atari-Games
공식 코드A quantum-classical reinforcement learning model to play Atari games
https://github.com/StatPhysBio/protein_holography-web
공식 코드HERMES: Holographic Equivariant neuRal network model for Mutational Effect and Stability prediction
https://github.com/StephenEkaputra/Swapped-Logit-Distillation
공식 코드https://github.com/Steven51516/FlexMol
공식 코드FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
https://github.com/SukwonYun/LTE4G
공식 코드https://github.com/SymbioticLab/FedScale
공식 코드FedScale: Benchmarking Model and System Performance of Federated Learning at Scale
https://github.com/SysCV/tet
공식 코드https://github.com/TAMU-VITA/AGD
공식 코드AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
https://github.com/TAU-MLwell/Rubust-Model-Compression
공식 코드https://github.com/TGB-Seq/TGB-Seq
공식 코드TGB-Seq Benchmark: Challenging Temporal GNNs with Complex Sequential Dynamics
https://github.com/THU-KEG/BIMR
공식 코드Is Multi-Hop Reasoning Really Explainable? Towards Benchmarking Reasoning Interpretability
https://github.com/THU-KEG/MAVEN-dataset
공식 코드https://github.com/THU-KEG/WaterBench
공식 코드WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.