https://github.com/skyshoumeng/m2skd
공식 코드Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation
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/slavovlab/scp_recommendations
공식 코드https://github.com/slds-lmu/qdo_yahpo
공식 코드https://github.com/slit-ai/adpa
공식 코드Advantage-Guided Distillation for Preference Alignment in Small Language Models
https://github.com/slyipae1/MedBookVQA
공식 코드MedBookVQA: A Systematic and Comprehensive Medical Benchmark Derived from Open-Access Book
https://github.com/sm4da/qemfi
공식 코드QeMFi: A Multifidelity Dataset of Quantum Chemical Properties of Diverse Molecules
https://github.com/smartyfh/llm-uncertainty-bench
공식 코드https://github.com/sming256/OpenTAD
공식 코드OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
https://github.com/smpl-env/smpl
공식 코드SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments
https://github.com/smplbody/hmr-benchmarks
공식 코드Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms
https://github.com/smsd75/redefining_normal_accv24
공식 코드Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection
https://github.com/snap-research/CAT
공식 코드Teachers Do More Than Teach: Compressing Image-to-Image Models
https://github.com/snap-research/graphless-neural-networks
공식 코드Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
https://github.com/snap-research/r2l
공식 코드https://github.com/snap-stanford/mlagentbench
공식 코드MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
https://github.com/snap-stanford/stark
공식 코드STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
https://github.com/snousias/Revisiting-Content-Based-Audio-Classification-for-Asthma-Medication-Adherence
공식 코드https://github.com/social-ai-studio/hatred
공식 코드https://github.com/social4rec/socialnet
공식 코드Social4Rec: Distilling User Preference from Social Graph for Video Recommendation in Tencent
https://github.com/socialfoundations/training-on-the-test-task
공식 코드Training on the Test Task Confounds Evaluation and Emergence
https://github.com/soda-inria/retrieve-merge-predict
공식 코드https://github.com/soda-inria/yadl
공식 코드https://github.com/solirinai/geobenchx
공식 코드https://github.com/somaminami/DCL
공식 코드https://github.com/songmzhang/dskd
공식 코드https://github.com/songmzhang/dskdv2
공식 코드A Dual-Space Framework for General Knowledge Distillation of Large Language Models
https://github.com/songmzhang/nmt-kd
공식 코드Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation
https://github.com/songrise/mllm4art
공식 코드https://github.com/sony/model_optimization
공식 코드EPTQ: Enhanced Post-Training Quantization via Hessian-guided Network-wise Optimization
https://github.com/sonyresearch/coala
공식 코드COALA: A Practical and Vision-Centric Federated Learning Platform
https://github.com/soombit-ai/chexgpt
공식 코드CheX-GPT: Harnessing Large Language Models for Enhanced Chest X-ray Report Labeling
https://github.com/soroorsh/deep-disaster
공식 코드Deep-Disaster: Unsupervised Disaster Detection and Localization Using Visual Data
https://github.com/sougata-ub/llms_for_ionic_liquids
공식 코드https://github.com/soumyabrata/ehr-features
공식 코드A predictive analytics approach for stroke prediction using machine learning and neural networks
https://github.com/soundclim/anuraset
공식 코드https://github.com/spacelearner/graph-gpt
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.