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/sxjscience/automl_multimodal_benchmark
공식 코드Benchmarking Multimodal AutoML for Tabular Data with Text Fields
https://github.com/szagoruyko/attention-transfer
공식 코드https://github.com/szc12153/cldyb
공식 코드CLDyB: Towards Dynamic Benchmarking for Continual Learning with Pre-trained Models
https://github.com/szq0214/MEAL-V2
공식 코드MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
https://github.com/szq0214/fkd
공식 코드A Fast Knowledge Distillation Framework for Visual Recognition
https://github.com/t0nyliang/EEGMobile
공식 코드https://github.com/taatiteam/motionencoders_parkinsonism_benchmark
공식 코드https://github.com/tablegpt/tablegpt-agent
공식 코드TableGPT2: A Large Multimodal Model with Tabular Data Integration
https://github.com/taco-group/autotrust
공식 코드AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving
https://github.com/taco-group/video-quality-assessment-a-comprehensive-survey
공식 코드https://github.com/taegyeong-lee/makd
공식 코드Multi-aspect Knowledge Distillation with Large Language Model
https://github.com/tagoyal/snac
공식 코드https://github.com/tailabtmu/uq_gnn
공식 코드https://github.com/taisazero/socratic-debugging-benchmark
공식 코드Can Language Models Employ the Socratic Method? Experiments with Code Debugging
https://github.com/talshaharabany/what-is-where-by-looking
공식 코드What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs
https://github.com/tamararruda/dnx
공식 코드Distill n' Explain: explaining graph neural networks using simple surrogates
https://github.com/tamlhp/dfd_benchmark
공식 코드A War Beyond Deepfake: Benchmarking Facial Counterfeits and Countermeasures
https://github.com/tangjialiang97/hidfd
공식 코드https://github.com/tanny411/trutheval
공식 코드TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability
https://github.com/tanvirnwu/hazespace2m
공식 코드https://github.com/tanvirnwu/trifuse
공식 코드LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond
https://github.com/tanyjiang/eoco
공식 코드A Unified Object Counting Network with Object Occupation Prior
https://github.com/tanyjiang/video_cil
공식 코드https://github.com/taohan10200/weather-5k
공식 코드How far are today's time-series models from real-world weather forecasting applications?
https://github.com/taowangzj/llformer
공식 코드Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method
https://github.com/taozh2017/knowsam
공식 코드https://github.com/taozhen1110/cudrt
공식 코드Towards Reliable Detection of LLM-Generated Texts: A Comprehensive Evaluation Framework with CUDRT
https://github.com/tapilot-crossing/tapilot_code
공식 코드Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents
https://github.com/tareknaous/readme
공식 코드ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment
https://github.com/taskography/taskography
공식 코드TASKOGRAPHY: Evaluating robot task planning over large 3D scene graphs
https://github.com/taucompling/bliss
공식 코드Benchmarking Neural Network Generalization for Grammar Induction
https://github.com/taveraantonio/pixda
공식 코드Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation
https://github.com/tcl9876/Denoising_Student
공식 코드Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed
https://github.com/tebmer/awesome-knowledge-distillation-of-llms
공식 코드https://github.com/teddy-xionggz/medrag
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.