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/ict-bigdatalab/rc-rag
공식 코드Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework
https://github.com/ict-bigdatalab/utility_judgments
공식 코드https://github.com/ictnlp/PTE-NMT
공식 코드Pruning-then-Expanding Model for Domain Adaptation of Neural Machine Translation
https://github.com/ictnlp/cokd
공식 코드https://github.com/ictnlp/ctc-s2ut
공식 코드CTC-based Non-autoregressive Textless Speech-to-Speech Translation
https://github.com/ictnlp/daspeech
공식 코드DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
https://github.com/ictnlp/ddrs-nat
공식 코드https://github.com/icu-sepsis/icu-sepsis
공식 코드https://github.com/idankinderman/fs_merge
공식 코드Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks
https://github.com/idea-iitd/gnnmerge
공식 코드GNNMerge: Merging of GNN Models Without Accessing Training Data
https://github.com/idea-iitd/mirage
공식 코드Mirage: Model-Agnostic Graph Distillation for Graph Classification
https://github.com/idea-research/dwpose
공식 코드Effective Whole-body Pose Estimation with Two-stages Distillation
https://github.com/idejie/KAD
공식 코드Active Object Detection with Knowledge Aggregation and Distillation from Large Models
https://github.com/idekerlab/llm_evaluation_for_gene_set_interpretation
공식 코드Evaluation of large language models for discovery of gene set function
https://github.com/idiap/sdialog
공식 코드SDialog: A Python Toolkit for Synthetic Dialogue Generation and Analysis
https://github.com/idogalil/benchmarking-uncertainty-estimation-performance
공식 코드https://github.com/idstcv/kda
공식 코드Improved Knowledge Distillation via Full Kernel Matrix Transfer
https://github.com/idt-iti/xai-video-summaries
공식 코드An Integrated Framework for Multi-Granular Explanation of Video Summarization
https://github.com/ieveresthd/sastc
공식 코드https://github.com/ifding/MLKD
공식 코드Multi-level Knowledge Distillation via Knowledge Alignment and Correlation
https://github.com/igor-morawski/raw-nod
공식 코드https://github.com/ihollywhy/DistillGCN.PyTorch
공식 코드https://github.com/ihp-lab/libreface
공식 코드LibreFace: An Open-Source Toolkit for Deep Facial Expression Analysis
https://github.com/iinemo/lm-polygraph
공식 코드Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph
https://github.com/iis-esslingen/vi-slam_lc_benchmark
공식 코드https://github.com/iiscleap/Audio-LLM-benchmarking-uncertainty
공식 코드Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning
https://github.com/ijcai2023/uni_kd
공식 코드Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data
https://github.com/ikeyang/ditu-net
공식 코드https://github.com/ikeyang/stu-net
공식 코드https://github.com/illaitar/based
공식 코드BASED: Benchmarking, Analysis, and Structural Estimation of Deblurring
https://github.com/illidanlab/abd
공식 코드Revisiting Data-Free Knowledge Distillation with Poisoned Teachers
https://github.com/illidanlab/cdrl
공식 코드https://github.com/ilyatyagin/dyport
공식 코드Dyport: Dynamic Importance-based Hypothesis Generation Benchmarking Technique
https://github.com/imagination-research/lbt
공식 코드Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study
https://github.com/imatif17/acia
공식 코드Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.