https://github.com/lancopku/dynamickd
공식 코드Dynamic Knowledge Distillation for Pre-trained Language Models
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/lancopku/gkd
공식 코드Gradient Knowledge Distillation for Pre-trained Language Models
https://github.com/land-fbk/benchmark-gen-explanations
공식 코드https://github.com/langtech-bsc/mt-evaluation
공식 코드MT-LENS: An all-in-one Toolkit for Better Machine Translation Evaluation
https://github.com/language-modeling-lab/TuringQ
공식 코드TuringQ: Benchmarking AI Comprehension in Theory of Computation
https://github.com/lanl/openfwi
공식 코드OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversion
https://github.com/lapisrocks/DiscreteAdversarialDistillation
공식 코드Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models
https://github.com/lasseufpa/caviar
공식 코드CAVIAR: Co-simulation of 6G Communications, 3D Scenarios and AI for Digital Twins
https://github.com/lasuomela/carla_vloc_benchmark
공식 코드https://github.com/launchnlp/ManyICLBench
공식 코드https://github.com/laurab222/tsad
공식 코드Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series
https://github.com/lawliet-zzl/ca
공식 코드https://github.com/layer6ai-labs/ssl-robustness
공식 코드Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
https://github.com/layneins/Zero-shot-RLHR
공식 코드https://github.com/lbaa2022/llmtaskplanning
공식 코드LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
https://github.com/lcastri/PeopleFlow
공식 코드Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments
https://github.com/lclarte/conformalamp.jl
공식 코드Building Conformal Prediction Intervals with Approximate Message Passing
https://github.com/lcs-crr/path
공식 코드https://github.com/lcs2-iiitd/gothate
공식 코드Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment
https://github.com/lcs2-iiitd/hatefinetune
공식 코드Probing Critical Learning Dynamics of PLMs for Hate Speech Detection
https://github.com/leaplabthu/checkpointkd
공식 코드https://github.com/learnedsystems/SOSD
공식 코드https://github.com/learninghx/tad-sr
공식 코드One Step Diffusion-based Super-Resolution with Time-Aware Distillation
https://github.com/legaldocumentprocessing/fir_dataset_icdar2023
공식 코드https://github.com/lehduong/kesi
공식 코드https://github.com/leiluk1/codesearcher
공식 코드https://github.com/leminhbinh0209/add
공식 코드https://github.com/leogrin/tabular-benchmark
공식 코드Why do tree-based models still outperform deep learning on tabular data?
https://github.com/leoiv/bencher
공식 코드Bencher: Simple and Reproducible Benchmarking for Black-Box Optimization
https://github.com/leolee99/injecguard
공식 코드InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
https://github.com/leolyliu/HOI4D-Instructions
공식 코드HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
https://github.com/leonchou5311/counterfactual-benchmark
공식 코드Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box
https://github.com/leonnnop/var
공식 코드https://github.com/leonsuarez24/dkdcis
공식 코드Distilling Knowledge for Designing Computational Imaging Systems
https://github.com/letian2003/c-vqa
공식 코드What If the TV Was Off? Examining Counterfactual Reasoning Abilities of Multi-modal Language Models
https://github.com/lewisclifton/mamba-wbc-classification
공식 코드Mamba-Based Ensemble learning for White Blood Cell Classification
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.