Papers with Code 아카이브

Knowledge Distillation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/jinglong696/secformer

공식 코드

SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC

https://github.com/jingminsun/prose_v1

공식 코드

Time-Series Forecasting, Knowledge Distillation, and Refinement within a Multimodal PDE Foundation Model

https://github.com/jingwu6/extended-agriculture-vision-dataset

공식 코드

Extended Agriculture-Vision: An Extension of a Large Aerial Image Dataset for Agricultural Pattern Analysis

https://github.com/jingyang2017/srd_ossl

공식 코드

Knowledge Distillation Meets Open-Set Semi-Supervised Learning

https://github.com/jingyi0000/vlm_survey

공식 코드

Vision-Language Models for Vision Tasks: A Survey

https://github.com/jinkyu032/FedMLB

공식 코드

Multi-Level Branched Regularization for Federated Learning

https://github.com/jinsuyoo/SSA-VSR

공식 코드

Self-Supervised Adaptation for Video Super-Resolution

https://github.com/jinzhuoran/rag-rewardbench

공식 코드

RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignment

https://github.com/jinzhuoran/rwku

공식 코드

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models

https://github.com/jitao-xu/tm-levt

공식 코드

Integrating Translation Memories into Non-Autoregressive Machine Translation

https://github.com/jitinkrishnan/transliteration-hindi-malayalam

공식 코드

Cross-Lingual Text Classification of Transliterated Hindi and Malayalam

https://github.com/jlianglab/benchmarktransferlearning

공식 코드

A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis

https://github.com/jmhb0/microvqa

공식 코드

MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research

https://github.com/jmiramont/mcsm-benchs

공식 코드

Benchmarking multi-component signal processing methods in the time-frequency plane

https://github.com/jo-wang/otta_vit_survey

공식 코드

In Search of Lost Online Test-time Adaptation: A Survey

https://github.com/job-sdf/benchmark

공식 코드

Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking

https://github.com/joeleelyf/ovo-bench

공식 코드

OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?

https://github.com/joeying1019/ultratool

공식 코드

Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios

https://github.com/joez17/videoniah

공식 코드

Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs

https://github.com/johndmendonca/maia-dqe

공식 코드

Dialogue Quality and Emotion Annotations for Customer Support Conversations

https://github.com/johndmendonca/medal

공식 코드

MEDAL: A Framework for Benchmarking LLMs as Multilingual Open-Domain Chatbots and Dialogue Evaluators

https://github.com/jokersio-tsy/autot2t

공식 코드

Automated Text-to-Table for Reasoning-Intensive Table QA: Pipeline Design and Benchmarking Insights

https://github.com/jonasschmidinger/limesoda_benchmarking

공식 코드

LimeSoDa: A Dataset Collection for Benchmarking of Machine Learning Regressors in Digital Soil Mapping

https://github.com/jonasschmidinger/limesoda_literature.review

공식 코드

LimeSoDa: A Dataset Collection for Benchmarking of Machine Learning Regressors in Digital Soil Mapping

https://github.com/jonatasbcchagas/aco_thop

공식 코드

Ants can orienteer a thief in their robbery

https://github.com/jonatasbcchagas/acoplusplus_thop

공식 코드

Efficiently solving the thief orienteering problem with a max-min ant colony optimization approach

https://github.com/jonathan-roberts1/SciFIBench

공식 코드

SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation

https://github.com/jongwooko/cr-ild

공식 코드

Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective

https://github.com/jongwooko/distillm

공식 코드

DistiLLM: Towards Streamlined Distillation for Large Language Models

https://github.com/joonaspu/video-game-behavioural-cloning

공식 코드

Benchmarking End-to-End Behavioural Cloning on Video Games

https://github.com/josangyeon/dsg-kd

공식 코드

DSG-KD: Knowledge Distillation from Domain-Specific to General Language Models

https://github.com/josedolz/MSL-student-becomes-master

공식 코드

Segmentation with mixed supervision: Confidence maximization helps knowledge distillation

https://github.com/josemiki/benchmarking_person_re_id

공식 코드

Benchmarking person re-identification datasets and approaches for practical real-world implementations

https://github.com/joshua-ren/better_supervisory_signal

공식 코드

Better Supervisory Signals by Observing Learning Paths

https://github.com/jovasque156/disparisk

공식 코드

DispaRisk: Auditing Fairness Through Usable Information

https://github.com/joyhsu0504/geoclidean_framework

공식 코드

Geoclidean: Few-Shot Generalization in Euclidean Geometry

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.