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/kevinkrahn/ancient-greek-datasets
공식 코드Sentence Embedding Models for Ancient Greek Using Multilingual Knowledge Distillation
https://github.com/kewei2023/ampcliff-generation
공식 코드AMPCliff: quantitative definition and benchmarking of activity cliffs in antimicrobial peptides
https://github.com/kexinhuang19/instructttseval
공식 코드https://github.com/kfoysalhaque/sawec
공식 코드https://github.com/khalil-research/arga-aaai23
공식 코드Graphs, Constraints, and Search for the Abstraction and Reasoning Corpus
https://github.com/khu-agi/privilege
공식 코드Pre-trained Vision and Language Transformers Are Few-Shot Incremental Learners
https://github.com/kiananvari/mtms-a-domain-adaptive-meta-knowledge-distillation-model-for-medical-image-classification
공식 코드https://github.com/kidist-amde/adv-kd
공식 코드Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling
https://github.com/kidzik/sweetrs-analysis
공식 코드https://github.com/kimsu55/begin
공식 코드Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark
https://github.com/kindredresearch/SenseAct
공식 코드Benchmarking Reinforcement Learning Algorithms on Real-World Robots
https://github.com/kingstdio/ECRECer
공식 코드https://github.com/kinit-sk/mAO
공식 코드Authorship Obfuscation in Multilingual Machine-Generated Text Detection
https://github.com/kinit-sk/mgt-detection-benchmark
공식 코드MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
https://github.com/kiribu10/openllminbpm-benchmark
공식 코드Towards a Benchmark for Large Language Models for Business Process Management Tasks
https://github.com/kirinng/dwb
공식 코드Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
https://github.com/kitamoto-lab/digital-typhoon
공식 코드https://github.com/kite99520/dialsummfactcorr
공식 코드https://github.com/klayand/pcka
공식 코드Rethinking Centered Kernel Alignment in Knowledge Distillation
https://github.com/kleinzcy/cr-kd-ncd
공식 코드Class-relation Knowledge Distillation for Novel Class Discovery
https://github.com/klusai/tinyfabulist
공식 코드TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Models
https://github.com/kminsoo/afc
공식 코드Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation
https://github.com/kmsamuel/cl-for-engineering-release
공식 코드Continual Learning Strategies for 3D Engineering Regression Problems: A Benchmarking Study
https://github.com/kmzzhang/deepCR-paper
공식 코드https://github.com/knodle/knodle
공식 코드https://github.com/knowledgetechnologyuhh/goal_conditioned_RL_baselines
공식 코드https://github.com/koeai/llvc
공식 코드https://github.com/kolkir/coarse_loftr_trt
공식 코드Local Feature Matching with Transformers for low-end devices
https://github.com/kota-dohi/dcase2022_task2_baseline_ae
공식 코드https://github.com/kota-dohi/dcase2022_task2_baseline_mobile_net_v2
공식 코드https://github.com/koushiksrivats/robust-concept-erasing
공식 코드STEREO: Towards Adversarially Robust Concept Erasing from Text-to-Image Generation Models
https://github.com/koutchemecharles/gaied_nips23
공식 코드https://github.com/kpeng9510/hopadiff
공식 코드https://github.com/kpeng9510/musclemap
공식 코드https://github.com/kpriyanshu256/polyglo-toxicity-prompts
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.