https://github.com/shuvenduroy/multimodal
공식 코드Benchmarking Vision-Language Contrastive Methods for Medical Representation Learning
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/shwai-he/ressa
공식 코드https://github.com/shwai-he/vlm-compression
공식 코드https://github.com/shyyhs/CourseraParallelCorpusMining
공식 코드Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation
https://github.com/si0wang/thinklite-vl
공식 코드SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
https://github.com/sianalytics/roar
공식 코드On Pitfalls of $\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective
https://github.com/siddheshih/culture-awareness-llms
공식 코드Survey of Cultural Awareness in Language Models: Text and Beyond
https://github.com/sign-language-processing/pose
공식 코드pose-format: Library for Viewing, Augmenting, and Handling .pose Files
https://github.com/signals-dev/Orion
공식 코드TadGAN: Time Series Anomaly Detection Using Generative Adversarial Networks
https://github.com/signetlabdei/sharp
공식 코드https://github.com/sihaoevery/tat
공식 코드https://github.com/sijieaaa/distilvpr
공식 코드DistilVPR: Cross-Modal Knowledge Distillation for Visual Place Recognition
https://github.com/simarkareer/unifiedvideoda
공식 코드We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline
https://github.com/simiaozuo/moebert
공식 코드MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation
https://github.com/simuenv/fedsikd
공식 코드https://github.com/sinc-lab/rna-llm-folding
공식 코드Comprehensive benchmarking of large language models for RNA secondary structure prediction
https://github.com/sinhala-nlp/nsina
공식 코드https://github.com/sinhala-nlp/sinhala-headline-generation
공식 코드https://github.com/sinhala-nlp/sinhala-news-category-prediction
공식 코드https://github.com/sinhala-nlp/sinhala-news-media-identification
공식 코드https://github.com/sintel-dev/orion
공식 코드AER: Auto-Encoder with Regression for Time Series Anomaly Detection
https://github.com/sisinflab/Ducho-meets-Elliot
공식 코드Ducho meets Elliot: Large-scale Benchmarks for Multimodal Recommendation
https://github.com/sisinflab/datarec
공식 코드DataRec: A Python Library for Standardized and Reproducible Data Management in Recommender Systems
https://github.com/sisinflab/ducho
공식 코드https://github.com/sisinflab/formal-multimod-rec
공식 코드Formalizing Multimedia Recommendation through Multimodal Deep Learning
https://github.com/sisinflab/llm-memoryinspector
공식 코드Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M
https://github.com/sislab-unitn/dyknow
공식 코드DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
https://github.com/siyi-wind/mdvit
공식 코드MDViT: Multi-domain Vision Transformer for Small Medical Image Segmentation Datasets
https://github.com/siyuyuan/coscript
공식 코드Distilling Script Knowledge from Large Language Models for Constrained Language Planning
https://github.com/sjmeis/mldp
공식 코드https://github.com/sjtu-chan-joey/battery-timer
공식 코드Foundation Models Knowledge Distillation For Battery Capacity Degradation Forecast
https://github.com/sjtu-omniagent/vocalbench
공식 코드VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models
https://github.com/sjtuxcx/ITES
공식 코드Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation
https://github.com/skelemoa/quovadis
공식 코드https://github.com/sktsherlock/atg
공식 코드When Graph meets Multimodal: Benchmarking on Multimodal Attributed Graphs Learning
https://github.com/skyshoumeng/Label_Assisted_Distillation
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.