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/tekdogan/iccbdc-21
공식 코드Benchmarking Apache Spark and Hadoop MapReduce on Big Data Classification
https://github.com/tencent-ailab/DrugOOD
공식 코드https://github.com/tencent-ailab/rlogist
공식 코드RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
https://github.com/tencent-alchemy/Alchemy
공식 코드Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
https://github.com/tensorflow/adanet
공식 코드Improving Neural Architecture Search Image Classifiers via Ensemble Learning
https://github.com/tensorflow/cleverhans
공식 코드Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
https://github.com/tensorflow/tpu
공식 코드Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
https://github.com/tensorflow/tpu/tree/master/models/official/detection/projects/vild
공식 코드Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
https://github.com/terarachang/ACCV_TinyGAN
공식 코드https://github.com/terarachang/memdata
공식 코드Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks
https://github.com/terarachang/mempi
공식 코드Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks
https://github.com/ternaus/robot-surgery-segmentation
공식 코드https://github.com/terra-quantum-public/tqcompressedgpt2
공식 코드TQCompressor: improving tensor decomposition methods in neural networks via permutations
https://github.com/testing-cs/codes
공식 코드CodeS: Towards Code Model Generalization Under Distribution Shift
https://github.com/testing-cs/codes-distribution-shift-benchmark-datasets
공식 코드CodeS: Towards Code Model Generalization Under Distribution Shift
https://github.com/testzer0/ambiqt
공식 코드Benchmarking and Improving Text-to-SQL Generation under Ambiguity
https://github.com/the-ai-alliance/geo-bench-vlm
공식 코드GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
https://github.com/the-finai/fino1
공식 코드Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance
https://github.com/theagentcompany/experiments
공식 코드TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
https://github.com/theagentcompany/theagentcompany
공식 코드TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
https://github.com/theeighthday/co-teaching
공식 코드Co-Teaching for Unsupervised Domain Adaptation and Expansion
https://github.com/theia-4869/bicross
공식 코드Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer
https://github.com/theislab/trVAE
공식 코드Conditional out-of-sample generation for unpaired data using trVAE
https://github.com/themoro/efficientsed
공식 코드Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models
https://github.com/thended32/analyzingfeatureextractors
공식 코드Analyzing the Feature Extractor Networks for Face Image Synthesis
https://github.com/thepanlab/NACHOS
공식 코드https://github.com/thinklab-sjtu/bench2drivezoo
공식 코드Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
https://github.com/thinklab-sjtu/predictiveco-benchmark
공식 코드Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime
https://github.com/thiviyant/intelligraphs
공식 코드IntelliGraphs: Datasets for Benchmarking Knowledge Graph Generation
https://github.com/thomasehuber/s5-rf
공식 코드Scaling Up Resonate-and-Fire Networks for Fast Deep Learning
https://github.com/thu-bpm/watermark-radioactivity-attack
공식 코드Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?
https://github.com/thu-coai/autodetect
공식 코드AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models
https://github.com/thu-coai/characterbench
공식 코드CharacterBench: Benchmarking Character Customization of Large Language Models
https://github.com/thu-coai/complexbench
공식 코드Benchmarking Complex Instruction-Following with Multiple Constraints Composition
https://github.com/thu-coai/da-transformer
공식 코드Directed Acyclic Transformer for Non-Autoregressive Machine Translation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.