https://github.com/wanliyoung/collapse-in-model-editing
공식 코드The Butterfly Effect of Model Editing: Few Edits Can Trigger Large Language Models Collapse
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/warisgill/FedDefender
공식 코드https://github.com/watermeloncq/drl-dynamic-optimization-portfolio-SB3py37
공식 코드https://github.com/wayveai/wayve_scenes
공식 코드WayveScenes101: A Dataset and Benchmark for Novel View Synthesis in Autonomous Driving
https://github.com/wbkit/scribbles4all
공식 코드Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
https://github.com/wchao0601/m4-sar
공식 코드https://github.com/wcx21/Social-Tasks-in-Sandbox-Simulation
공식 코드Towards Objectively Benchmarking Social Intelligence for Language Agents at Action Level
https://github.com/wdika/atommic
공식 코드https://github.com/wearepal/okapi
공식 코드Okapi: Generalising Better by Making Statistical Matches Match
https://github.com/webpai/interaction2code
공식 코드https://github.com/weiganglu/adagmlp-kdd24
공식 코드https://github.com/weijiawu/cisdq
공식 코드Continual Learning for Image Segmentation with Dynamic Query
https://github.com/weilllllls/onpro
공식 코드https://github.com/weipingfu/qgeval
공식 코드QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation
https://github.com/weiqingq/CLRKDNet
공식 코드CLRKDNet: Speeding up Lane Detection with Knowledge Distillation
https://github.com/weixi-feng/tc-bench
공식 코드TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation
https://github.com/weixin-liang/metashift
공식 코드https://github.com/weiyifan1023/senator
공식 코드Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs
https://github.com/weiyuchen1999/LGISS
공식 코드https://github.com/weizhenliubioinform/fish-phenotype-detect
공식 코드https://github.com/wencheng-zhu/ckd
공식 코드CKD: Contrastive Knowledge Distillation from A Sample-wise Perspective
https://github.com/wengbenjue/llms-peft-cook
공식 코드https://github.com/wenhuchen/time-sensitive-qa
공식 코드https://github.com/wenjiedu/awesome_imputation
공식 코드https://github.com/wennyxy/dino-mc
공식 코드Extending global-local view alignment for self-supervised learning with remote sensing imagery
https://github.com/wenzhengzhang/entqa
공식 코드https://github.com/werkaaa/iscm
공식 코드https://github.com/westlake-repl/microlens
공식 코드A Content-Driven Micro-Video Recommendation Dataset at Scale
https://github.com/westlake-repl/pixelrec
공식 코드An Image Dataset for Benchmarking Recommender Systems with Raw Pixels
https://github.com/whdong-whu/sikd
공식 코드Shape-intensity knowledge distillation for robust medical image segmentation
https://github.com/whopriyam/Benchmarking-Differential-Privacy-and-Federated-Learning-for-BERT-Models
공식 코드Benchmarking Differential Privacy and Federated Learning for BERT Models
https://github.com/whu-zqh/atkd
공식 코드Revisiting Knowledge Distillation for Autoregressive Language Models
https://github.com/whu-zqh/panda
공식 코드PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
https://github.com/wildltr/ptranking
공식 코드PT-Ranking: A Benchmarking Platform for Neural Learning-to-Rank
https://github.com/williamcorrias/maya-password-benchmarking
공식 코드MAYA: Addressing Inconsistencies in Generative Password Guessing through a Unified Benchmark
https://github.com/williamgilpin/dysts
공식 코드Chaos as an interpretable benchmark for forecasting and data-driven modelling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.