Papers with Code 아카이브

Mixture-of-Experts

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/imagination-research/eep

공식 코드

Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

https://github.com/ink-usc/crosstaskmoe

공식 코드

Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts

https://github.com/ise-uiuc/xft

공식 코드

XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts

https://github.com/ist-daslab/qmoe

공식 코드

QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models

https://github.com/james-oldfield/mmoe

공식 코드

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

https://github.com/james-oldfield/mumoe

공식 코드

Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization

https://github.com/jasoncodemaker/ctvr

공식 코드

StableFusion: Continual Video Retrieval via Frame Adaptation

https://github.com/jasonz5/STGormer

공식 코드

Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting

https://github.com/jefferyjiang-yf/m4oe

공식 코드

M$^4$oE: A Foundation Model for Medical Multimodal Image Segmentation with Mixture of Experts

https://github.com/jeongeun980906/uncertainty-aware-robust-learning

공식 코드

Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation

https://github.com/jiangfeng1124/transfer

공식 코드

Multi-Source Domain Adaptation with Mixture of Experts

https://github.com/jiangsongtao/med-moe

공식 코드

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models

https://github.com/jiangsongtao/tinymed

공식 코드

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models

https://github.com/jiazuoyu/moe-adapters4cl

공식 코드

Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters

https://github.com/jieshibo/mole

공식 코드

Mixture of Lookup Experts

https://github.com/jinga-lala/damex

공식 코드

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

https://github.com/jingjing12110/mixphm

공식 코드

MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering

https://github.com/jinyan-06/shike

공식 코드

Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation

https://github.com/joelowj/unified_mom_mmoe

공식 코드

DeepUnifiedMom: Unified Time-series Momentum Portfolio Construction via Multi-Task Learning with Multi-Gate Mixture of Experts

https://github.com/johnarevalo/gmu-mmimdb

공식 코드

Gated Multimodal Units for Information Fusion

https://github.com/jonathanbrok/manifold-induced-biases-for-zero-shot-and-few-shot-detection-of-generated-images

공식 코드

Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images

https://github.com/jose3g/Learning_CHARME_models_with_DNN

공식 코드

Learning CHARME models with neural networks

https://github.com/jp-25/end-to-end-adaptive-local-leanring-tall-

공식 코드

Countering Mainstream Bias via End-to-End Adaptive Local Learning

https://github.com/jsuarez5341/Efficient-Dynamic-Batching

공식 코드

Effective Approaches to Batch Parallelization for Dynamic Neural Network Architectures

https://github.com/jxliu-ai/medcot

공식 코드

MedCoT: Medical Chain of Thought via Hierarchical Expert

https://github.com/kaihuhuang/language-group

공식 코드

Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing

https://github.com/kamanphoebe/look-into-moes

공식 코드

A Closer Look into Mixture-of-Experts in Large Language Models

https://github.com/kamanphoebe/m2mkd

공식 코드

m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers

https://github.com/kastel-mobilitylab/mixtures-of-experts

공식 코드

Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation

https://github.com/kennqiang/mdfend-weibo21

공식 코드

MDFEND: Multi-domain Fake News Detection

https://github.com/kongyilun/m3dt

공식 코드

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer

https://github.com/lancercat/moose

공식 코드

MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition

https://github.com/lcs2-iiitd/gothate

공식 코드

Revisiting Hate Speech Benchmarks: From Data Curation to System Deployment

https://github.com/leej35/residual-moe

공식 코드

Learning to Adapt Clinical Sequences with Residual Mixture of Experts

https://github.com/leiyuzhu/capacitypredict

공식 코드

A multi-scale lithium-ion battery capacity prediction using mixture of experts and patch-based MLP

https://github.com/lgordon99/fusion-strategies-eccv

공식 코드

Multimodal Fusion Strategies for Mapping Biophysical Landscape Features

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