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/kaiqi123/sqakd
공식 코드https://github.com/kaistmm/voxsim_trainer
공식 코드https://github.com/kaiwenw/JoinGym
공식 코드JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning
https://github.com/kaiyangzhou/on-device-dg
공식 코드https://github.com/kaka0910/M4Fog
공식 코드https://github.com/kakaobrain/chexgpt
공식 코드CheX-GPT: Harnessing Large Language Models for Enhanced Chest X-ray Report Labeling
https://github.com/kalviny/IMTA
공식 코드https://github.com/kamanphoebe/m2mkd
공식 코드m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers
https://github.com/kamilazdybal/local-manifold-learning
공식 코드Local manifold learning and its link to domain-based physics knowledge
https://github.com/kananmahammadli/sllmbo
공식 코드Sequential Large Language Model-Based Hyper-parameter Optimization
https://github.com/kanishkamisra/minicons
공식 코드minicons: Enabling Flexible Behavioral and Representational Analyses of Transformer Language Models
https://github.com/kanishkg/boxing-gym
공식 코드BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery
https://github.com/kanyooo/biomed-dpt
공식 코드Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models
https://github.com/kapilw25/Evaluation_generated_images
공식 코드Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models
https://github.com/karanchahal/distiller
공식 코드https://github.com/karim-53/compare-xai
공식 코드https://github.com/karl-zhao/benchmarking-gnns-pyg
공식 코드https://github.com/karttikeya/minrev
공식 코드https://github.com/katarinayuan/structtokenbench
공식 코드https://github.com/kathrinse/math-reasoning-benchmark
공식 코드https://github.com/katiebuc/gnnad
공식 코드Graph Neural Network-Based Anomaly Detection for River Network Systems
https://github.com/katyafilimoshina/glgenn
공식 코드https://github.com/kaustubhshejole/stereodetect
공식 코드Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinnings
https://github.com/kcyu2014/lidar-camera-robust-benchmark
공식 코드Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection
https://github.com/kdd-lab/XAI-Survey
공식 코드Benchmarking and Survey of Explanation Methods for Black Box Models
https://github.com/kdexd/coco-rem
공식 코드https://github.com/kdst-team/naturalinversion
공식 코드NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency
https://github.com/kei813121/atkd
공식 코드Adaptive Temperature Based on Logits Correlation in Knowledge Distillation
https://github.com/keiserlab/rcav
공식 코드Robust Semantic Interpretability: Revisiting Concept Activation Vectors
https://github.com/kennethborup/gaussian_process_self_distillation
공식 코드Self-Distillation for Gaussian Process Regression and Classification
https://github.com/kennethlimjf/contrastive-learning-in-distilled-models
공식 코드https://github.com/kenqgu/radar
공식 코드RADAR: Benchmarking Language Models on Imperfect Tabular Data
https://github.com/kerenfu/LFSOD-Survey
공식 코드Light Field Salient Object Detection: A Review and Benchmark
https://github.com/keshik6/HourVideo
공식 코드https://github.com/kevin-lkw/loopnav
공식 코드Toward Memory-Aided World Models: Benchmarking via Spatial Consistency
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.