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/mikivishy/fullfront
공식 코드FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
https://github.com/mikudehuane/FedLaAvg
공식 코드Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability
https://github.com/mila-iqia/milabench
공식 코드https://github.com/mineanybuild/mineanybuild
공식 코드MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
https://github.com/minerllabs/basalt-benchmark
공식 코드https://github.com/ming053l/csakd
공식 코드https://github.com/minghehe-nobug/svip
공식 코드Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program
https://github.com/mingjiewang0606/fedcl_pubic
공식 코드FedCL: Federated Multi-Phase Curriculum Learning to Synchronously Correlate User Heterogeneity
https://github.com/mingsun-tse/awesome-pruning-at-initialization
공식 코드https://github.com/mingsun-tse/collaborative-distillation
공식 코드Collaborative Distillation for Ultra-Resolution Universal Style Transfer
https://github.com/mingsun-tse/good-da-in-kd
공식 코드What Makes a "Good" Data Augmentation in Knowledge Distillation -- A Statistical Perspective
https://github.com/mingsun-tse/smile-pruning
공식 코드https://github.com/minhyeok01/pynet-qxq
공식 코드PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors
https://github.com/minipuding/fastmrt
공식 코드https://github.com/minjiyoon/cgt
공식 코드Graph Generative Model for Benchmarking Graph Neural Networks
https://github.com/minnesotanlp/cobbler
공식 코드Benchmarking Cognitive Biases in Large Language Models as Evaluators
https://github.com/minqi/wordcraft
공식 코드WordCraft: An Environment for Benchmarking Commonsense Agents
https://github.com/mirbostani/QA-KD-AL
공식 코드Improving Question Answering Performance Using Knowledge Distillation and Active Learning
https://github.com/misahub2023/benchmarking-codes-of-the-wcebleedgen-dataset
공식 코드https://github.com/misahub2023/capsule-vision-2024-challenge
공식 코드Capsule Vision 2024 Challenge: Multi-Class Abnormality Classification for Video Capsule Endoscopy
https://github.com/mismayil/crow
공식 코드CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks
https://github.com/mit-han-lab/efficientvit
공식 코드EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss
https://github.com/mit-han-lab/neurips-micronet
공식 코드https://github.com/mit-wu-lab/IntersectionZoo
공식 코드IntersectionZoo: Eco-driving for Benchmarking Multi-Agent Contextual Reinforcement Learning
https://github.com/mitibmxgraph/revtrack
공식 코드https://github.com/mitmedialab/medical_hallucination
공식 코드Medical Hallucinations in Foundation Models and Their Impact on Healthcare
https://github.com/mitscha/strassennets
공식 코드https://github.com/mitvis/abstraction-alignment
공식 코드Abstraction Alignment: Comparing Model-Learned and Human-Encoded Conceptual Relationships
https://github.com/miulab/pairdistill
공식 코드PairDistill: Pairwise Relevance Distillation for Dense Retrieval
https://github.com/mkallipo/affiliation-matching
공식 코드https://github.com/mkartik/Shallow-UWnet
공식 코드Shallow-UWnet : Compressed Model for Underwater Image Enhancement
https://github.com/mklimasz/transferable-modularity
공식 코드Is Modularity Transferable? A Case Study through the Lens of Knowledge Distillation
https://github.com/ml-energy/leaderboard
공식 코드The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization
https://github.com/ml-research/cake
공식 코드https://github.com/mlai-yonsei/exceptionalbenchmark
공식 코드Benchmarking Foundation Models on Exceptional Cases: Dataset Creation and Validation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.