https://github.com/fuchs-lab-public/cpath_sabenchmark
공식 코드Benchmarking Embedding Aggregation Methods in Computational Pathology: A Clinical Data Perspective
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/fuchuanqu/gianthunter
공식 코드https://github.com/fudanselab/linuxflbench
공식 코드Benchmarking and Enhancing LLM Agents in Localizing Linux Kernel Bugs
https://github.com/fudanvi/benchmarking-chinese-text-recognition
공식 코드Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study
https://github.com/fudanvi/fudanocr
공식 코드Orientation-Independent Chinese Text Recognition in Scene Images
https://github.com/fudanvi/maecho
공식 코드https://github.com/funalab/pipebo
공식 코드https://github.com/fvasluianu97/ifblend
공식 코드https://github.com/fy-vision/diga
공식 코드DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentation
https://github.com/g-taxonomy-workgroup/gtaxogym
공식 코드https://github.com/g8a9/ferret
공식 코드ferret: a Framework for Benchmarking Explainers on Transformers
https://github.com/gaabrielfranco/llp-variants-datasets-benchmarks
공식 코드https://github.com/gabinsane/multimodal-vae-comparison
공식 코드Benchmarking Multimodal Variational Autoencoders: CdSprites+ Dataset and Toolkit
https://github.com/gagan3012/eais-temporal-bias
공식 코드DateLogicQA: Benchmarking Temporal Biases in Large Language Models
https://github.com/gagolews/clustering-benchmarks
공식 코드https://github.com/gagolews/clustering-data-v1
공식 코드https://github.com/gagolews/clustering-results-v1
공식 코드https://github.com/gair-nlp/behonest
공식 코드https://github.com/gair-nlp/benbench
공식 코드https://github.com/gair-nlp/o1-journey
공식 코드https://github.com/gair-nlp/olympicarena
공식 코드OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
https://github.com/gaotiexinqu/v2p-bench
공식 코드https://github.com/gatech-eic/longmamba
공식 코드LongMamba: Enhancing Mamba's Long Context Capabilities via Training-Free Receptive Field Enlargement
https://github.com/gauzias/sulcal_graphs_matching
공식 코드Population-wise Labeling of Sulcal Graphs using Multi-graph Matching
https://github.com/gayathrimatcha/sft-kd-recon
공식 코드https://github.com/gayecolakoglu/layie-llm
공식 코드Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMs
https://github.com/gbibbo/voice_anonymization
공식 코드The Sounds of Home: A Speech-Removed Residential Audio Dataset for Sound Event Detection
https://github.com/gbrltv/business_process_encoding
공식 코드https://github.com/gdmnl/spectral-gnn-benchmark
공식 코드Benchmarking Spectral Graph Neural Networks: A Comprehensive Study on Effectiveness and Efficiency
https://github.com/geek-ai/Texygen
공식 코드https://github.com/geflaspohler/poold
공식 코드https://github.com/gemcollector/learning-from-scratch
공식 코드On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline
https://github.com/genentech/ringer
공식 코드https://github.com/genezc/minidisc
공식 코드MiniDisc: Minimal Distillation Schedule for Language Model Compression
https://github.com/genezc/minimoe
공식 코드Lifting the Curse of Capacity Gap in Distilling Language Models
https://github.com/genezc/structbias
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.