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/mlcommons/ck
공식 코드https://github.com/mlcommons/cm4mlops
공식 코드https://github.com/mlcommons/medical
공식 코드MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation
https://github.com/mlcommons/tiny
공식 코드https://github.com/mlfoundations/tableshift
공식 코드Benchmarking Distribution Shift in Tabular Data with TableShift
https://github.com/mlivanos/cooperative-knowledge-distillation
공식 코드Cooperative Knowledge Distillation: A Learner Agnostic Approach
https://github.com/mllmkcbench/mllmkc
공식 코드Benchmarking Multimodal Knowledge Conflict for Large Multimodal Models
https://github.com/mlperf/training
공식 코드https://github.com/mlr-org/mlr3inferr
공식 코드Constructing Confidence Intervals for 'the' Generalization Error -- a Comprehensive Benchmark Study
https://github.com/mlsysops/migprofiler
공식 코드https://github.com/mludkov/mlOSP
공식 코드mlOSP: Towards a Unified Implementation of Regression Monte Carlo Algorithms
https://github.com/mm4spa/eigd
공식 코드A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games
https://github.com/mmajurski/grounded-synth-lm-benchmark
공식 코드Grounding Synthetic Data Evaluations of Language Models in Unsupervised Document Corpora
https://github.com/mmalekzadeh/honest-but-curious-nets
공식 코드https://github.com/mmasana/FACIL
공식 코드Causes of Catastrophic Forgetting in Class-Incremental Semantic Segmentation
https://github.com/mmdocrag/mmdocrag
공식 코드Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering
https://github.com/mmic-lcl/datasets-and-benchmark-code
공식 코드https://github.com/mmlab-unitn/truefake-ijcnn25
공식 코드TrueFake: A Real World Case Dataset of Last Generation Fake Images also Shared on Social Networks
https://github.com/mmorafah/takfl
공식 코드Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration
https://github.com/mmschlk/shapiq
공식 코드https://github.com/mmtu-benchmark/mmtu
공식 코드MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
https://github.com/model-glue/model-glue
공식 코드Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
https://github.com/modelstreaming/ams
공식 코드Real-Time Video Inference on Edge Devices via Adaptive Model Streaming
https://github.com/modeltc/llmc
공식 코드LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit
https://github.com/moe-inf/awesome-moe-inference
공식 코드A Survey on Inference Optimization Techniques for Mixture of Experts Models
https://github.com/moeinsorkhei/csaw-m_annotation_tool
공식 코드CSAW-M: An Ordinal Classification Dataset for Benchmarking Mammographic Masking of Cancer
https://github.com/mohamedelrefaie/drivaernet
공식 코드https://github.com/mohammadrezabanaei/lora-xs
공식 코드LoRA-XS: Low-Rank Adaptation with Extremely Small Number of Parameters
https://github.com/molden/atomlenz
공식 코드Atom-Level Optical Chemical Structure Recognition with Limited Supervision
https://github.com/molecularmodelinglab/bigbind
공식 코드An Improved Metric and Benchmark for Assessing the Performance of Virtual Screening Models
https://github.com/molecularmodelinglab/plantain
공식 코드PLANTAIN: Diffusion-inspired Pose Score Minimization for Fast and Accurate Molecular Docking
https://github.com/molecularsets/moses
공식 코드Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
https://github.com/moment-timeseries-foundation-model/timeseriesgym
공식 코드TimeSeriesGym: A Scalable Benchmark for (Time Series) Machine Learning Engineering Agents
https://github.com/montaserFath/Reinforcement-Learning-for-Prosthetics
공식 코드https://github.com/moonshotai/combibench
공식 코드CombiBench: Benchmarking LLM Capability for Combinatorial Mathematics
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.