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/ahwang16/grounded-intuition-gpt-vision
공식 코드Grounded Intuition of GPT-Vision's Abilities with Scientific Images
https://github.com/ahxt/fair_fairness_benchmark
공식 코드FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
https://github.com/ai-agents-2030/SPA-Bench
공식 코드SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation
https://github.com/ai-da-stc/generative-ai-research-babylm
공식 코드https://github.com/ai-lab-y/nn_cryptanalytic_extraction
공식 코드Hard-Label Cryptanalytic Extraction of Neural Network Models
https://github.com/ai4bharat/cia
공식 코드Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs
https://github.com/ai4ce/DiscoNet
공식 코드Learning Distilled Collaboration Graph for Multi-Agent Perception
https://github.com/ai4ce/SNAC
공식 코드Simultaneous Navigation and Construction Benchmarking Environments
https://github.com/ai4ce/loqi-vpr
공식 코드Distillation Improves Visual Place Recognition for Low Quality Images
https://github.com/ai4finance-foundation/fingpt
공식 코드FinGPT: Instruction Tuning Benchmark for Open-Source Large Language Models in Financial Datasets
https://github.com/ai4healthuol/mds-ed
공식 코드https://github.com/ai4healthuol/ppg-ood-generalization
공식 코드https://github.com/ai4life-group/openxai
공식 코드OpenXAI: Towards a Transparent Evaluation of Model Explanations
https://github.com/aicenter/ridesharing_darp_instances
공식 코드Large-scale Ridesharing DARP Instances Based on Real Travel Demand
https://github.com/aichipdesign/chipgptv
공식 코드Natural language is not enough: Benchmarking multi-modal generative AI for Verilog generation
https://github.com/aiconslab/roodmri
공식 코드https://github.com/aida-ugent/NRL4LP
공식 코드Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?
https://github.com/aidos-lab/MANTRA
공식 코드https://github.com/aidos-lab/rings
공식 코드No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasets
https://github.com/aieson/crossmatch
공식 코드https://github.com/aifeg/benchgpt
공식 코드BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models
https://github.com/aifeg/benchlmm
공식 코드BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models
https://github.com/aiflames/flames
공식 코드https://github.com/aiforsec/secure
공식 코드SECURE: Benchmarking Large Language Models for Cybersecurity
https://github.com/aifsr/2023-benchmarking
공식 코드Improvements & Evaluations on the MLCommons CloudMask Benchmark
https://github.com/aiha-lab/tsld
공식 코드Token-Scaled Logit Distillation for Ternary Weight Generative Language Models
https://github.com/ailab-cvc/seed-bench
공식 코드SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension
https://github.com/ailabdsunipi/pymarlzooplus
공식 코드https://github.com/aim-uofa/OIR
공식 코드https://github.com/aim-uofa/geobench
공식 코드GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models
https://github.com/aimagelab/VKD
공식 코드Robust Re-Identification by Multiple Views Knowledge Distillation
https://github.com/aimagelab/camel
공식 코드https://github.com/aimagelab/mammoth
공식 코드Dark Experience for General Continual Learning: a Strong, Simple Baseline
https://github.com/aiot-lab-bkai/oro-ccgrid2023-cadis
공식 코드https://github.com/aiot-mlsys-lab/fedaiot
공식 코드FedAIoT: A Federated Learning Benchmark for Artificial Intelligence of Things
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.