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/zjukg/kg-llm-papers
공식 코드https://github.com/zjukg/lpkg
공식 코드Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphs
https://github.com/zjunlp/easyedit
공식 코드https://github.com/zjunlp/factchd
공식 코드FactCHD: Benchmarking Fact-Conflicting Hallucination Detection
https://github.com/zjunlp/worfbench
공식 코드https://github.com/zk2172-columbia/constellation-dataset
공식 코드Constellation Dataset: Benchmarking High-Altitude Object Detection for an Urban Intersection
https://github.com/zkxufo/TTM
공식 코드Knowledge Distillation Based on Transformed Teacher Matching
https://github.com/zli12321/qa_metrics
공식 코드PEDANTS: Cheap but Effective and Interpretable Answer Equivalence
https://github.com/zlwang-cs/OfficeBench
공식 코드OfficeBench: Benchmarking Language Agents across Multiple Applications for Office Automation
https://github.com/zma-c-137/VarGFaceNet
공식 코드https://github.com/zo-bench/zo-llm
공식 코드Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark
https://github.com/zoeparman/benchmark-general-imaging
공식 코드https://github.com/zoeyyao27/gkt
공식 코드https://github.com/zou-longkun/rpd
공식 코드Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers
https://github.com/zouharvi/vocab-stealing
공식 코드Stolen Subwords: Importance of Vocabularies for Machine Translation Model Stealing
https://github.com/zpengmei/xxmd
공식 코드https://github.com/zpf0117b/CLMB
공식 코드CLMB: deep contrastive learning for robust metagenomic binning
https://github.com/zqiao11/tscil
공식 코드Class-incremental Learning for Time Series: Benchmark and Evaluation
https://github.com/zrqiao/NeuralPLexer
공식 코드State-specific protein-ligand complex structure prediction with a multi-scale deep generative model
https://github.com/zuchniakk/mtkd
공식 코드https://github.com/zuchniakk/votingalgorithms
공식 코드https://github.com/zurichnlp/bless
공식 코드BLESS: Benchmarking Large Language Models on Sentence Simplification
https://github.com/zwang84/zsdb3kd
공식 코드Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model
https://github.com/zwt233/ROD
공식 코드https://github.com/zxc2012/flowdistill
공식 코드FlowDistill: Scalable Traffic Flow Prediction via Distillation from LLMs
https://github.com/zxk1212/concealgs
공식 코드ConcealGS: Concealing Invisible Copyright Information in 3D Gaussian Splatting
https://github.com/zxlovely/FedKF
공식 코드Handling Data Heterogeneity in Federated Learning via Knowledge Distillation and Fusion
https://github.com/zxuandang/atd-via-flows
공식 코드Semi-Supervised Learning for Anomaly Traffic Detection via Bidirectional Normalizing Flows
https://github.com/zyn-1101/dandr
공식 코드https://github.com/zzhangsm/ookd
공식 코드https://github.com/zzoomd/fairgkd
공식 코드The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation
https://github.com/zzy-zhou/dsec-mos
공식 코드Event-Free Moving Object Segmentation from Moving Ego Vehicle
https://github.com/zzz47zzz/codebase-for-incremental-learning-with-llm
공식 코드https://gitlab.com/micronano_public/tb-mlff
공식 코드Evaluating the Transferability of Machine-Learned Force Fields for Material Property Modeling
https://gitlab.com/mit-mers/safe-visual-mapf
공식 코드Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.