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/yoqim/pose_vireid
공식 코드https://github.com/yoshitomo-matsubara/sc2-benchmark
공식 코드https://github.com/yoshitomo-matsubara/supervised-compression
공식 코드Supervised Compression for Resource-Constrained Edge Computing Systems
https://github.com/yoshitomo-matsubara/torchdistill
공식 코드torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation
https://github.com/youjie-zhou/fmf-slam
공식 코드https://github.com/youngsoul0731/flora-bench
공식 코드https://github.com/yqc123456/hkd_for_person_search
공식 코드Ground-to-Aerial Person Search: Benchmark Dataset and Approach
https://github.com/yrf1/llm-massivemulticulturenormsknowledge-nclb
공식 코드Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking
https://github.com/ys-zong/medfair
공식 코드https://github.com/ys-zong/vl-icl
공식 코드VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning
https://github.com/yshMars/DistilPose
공식 코드DistilPose: Tokenized Pose Regression with Heatmap Distillation
https://github.com/ytian73/aigi-vc
공식 코드AI-generated Image Quality Assessment in Visual Communication
https://github.com/yuanggeng/bridging-dimensions
공식 코드Bridging Dimensions: Confident Reachability for High-Dimensional Controllers
https://github.com/yuangpeng/dreambench_plus
공식 코드DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation
https://github.com/yuanli2333/Teacher-free-Knowledge-Distillation
공식 코드Revisiting Knowledge Distillation via Label Smoothing Regularization
https://github.com/yuanyuanlei-nlp/propaganda_emnlp_2023
공식 코드Discourse Structures Guided Fine-grained Propaganda Identification
https://github.com/yuchen005/robustger
공식 코드Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
https://github.com/yueeeeeeee/recsys-extraction-attack
공식 코드Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
https://github.com/yuelinan/codes-of-c2r
공식 코드Cooperative Classification and Rationalization for Graph Generalization
https://github.com/yueliukth/csaw-m
공식 코드CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer
https://github.com/yueming-yin/gafse
공식 코드An open unified deep graph learning framework for discovering drug leads
https://github.com/yueqingliang1/unbench
공식 코드Benchmarking LLMs for Political Science: A United Nations Perspective
https://github.com/yuki-asuuna/umwp
공식 코드Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem
https://github.com/yukimasano/PASS
공식 코드PASS: An ImageNet replacement for self-supervised pretraining without humans
https://github.com/yukimasano/single-img-extrapolating
공식 코드The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
https://github.com/yuliang-liu/multimodalocr
공식 코드https://github.com/yumo216/dgekt
공식 코드DGEKT: A Dual Graph Ensemble Learning Method for Knowledge Tracing
https://github.com/yun224/dukd
공식 코드Data Upcycling Knowledge Distillation for Image Super-Resolution
https://github.com/yunpeng-zhao/syndata-privacy
공식 코드https://github.com/yunqing-me/Born-Again-FS
공식 코드FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification
https://github.com/yuntaeyang/telme
공식 코드TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation
https://github.com/yurifacanha/llmquoter
공식 코드LLMQuoter: Enhancing RAG Capabilities Through Efficient Quote Extraction From Large Contexts
https://github.com/yusaemeow/collab-overcooked
공식 코드Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
https://github.com/yushan-huang/microt
공식 코드https://github.com/yushansu/prumux
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.