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/0930mcx/guiding-experts

공식 코드

Guiding the Experts: Semantic Priors for Efficient and Focused MoE Routing

https://github.com/2448845600/kan4tsf

공식 코드

KAN4TSF: Are KAN and KAN-based models Effective for Time Series Forecasting?

https://github.com/24davidhuang/emotion-qwen

공식 코드

Emotion-Qwen: Training Hybrid Experts for Unified Emotion and General Vision-Language Understanding

https://github.com/924973292/demo

공식 코드

DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification

https://github.com/AI-14/micar-vl-moe

공식 코드

MicarVLMoE: A Modern Gated Cross-Aligned Vision-Language Mixture of Experts Model for Medical Image Captioning and Report Generation

https://github.com/AIM-SKKU/QA-TIGER

공식 코드

Question-Aware Gaussian Experts for Audio-Visual Question Answering

https://github.com/AVBochkov/Embeddings

공식 코드

Growing Transformers: Modular Composition and Layer-wise Expansion on a Frozen Substrate

https://github.com/AhmedMagdyHendawy/MOORE

공식 코드

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts

https://github.com/BenChaliah/Superposition-Transformer

공식 코드

Superposition in Transformers: A Novel Way of Building Mixture of Experts

https://github.com/BorealisAI/MMoEEx-MTL

공식 코드

Heterogeneous Multi-task Learning with Expert Diversity

https://github.com/ByungKwanLee/MoAI

공식 코드

MoAI: Mixture of All Intelligence for Large Language and Vision Models

https://github.com/CyberAgentAILab/posthoc-control-moe

공식 코드

Not Eliminate but Aggregate: Post-Hoc Control over Mixture-of-Experts to Address Shortcut Shifts in Natural Language Understanding

https://github.com/DanWaxman/Lintel

공식 코드

A Gaussian Process-based Streaming Algorithm for Prediction of Time Series With Regimes and Outliers

https://github.com/Fraunhofer-AISEC/ARGUE

공식 코드

Anomaly Detection by Recombining Gated Unsupervised Experts

https://github.com/Fsoft-AIC/LibMoE

공식 코드

LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models

https://github.com/GISec-Team/GNNMoE

공식 코드

Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification

https://github.com/Gleghorn-Lab/mixture-of-experts-sentence-similarity

공식 코드

Contrastive Learning and Mixture of Experts Enables Precise Vector Embeddings

https://github.com/Hannibal046/xRAG

공식 코드

xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token

https://github.com/HongyangLL/M3-JEPA

공식 코드

M3-Jepa: Multimodal Alignment via Multi-directional MoE based on the JEPA framework

https://github.com/Hugo-Zhu/MvP

공식 코드

Integrating Multi-view Analysis: Multi-view Mixture-of-Expert for Textual Personality Detection

https://github.com/IMPLabUniPr/swin2-mose

공식 코드

Swin2-MoSE: A New Single Image Super-Resolution Model for Remote Sensing

https://github.com/IsDling/CFDL

공식 코드

Completed Feature Disentanglement Learning for Multimodal MRIs Analysis

https://github.com/JarvisPei/CMoE

공식 코드

CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference

https://github.com/JayZhang42/SLED

공식 코드

SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models

https://github.com/JieRen98/rlkit-pmoe

공식 코드

Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning

https://github.com/Kenyaggel/MLoRA

공식 코드

MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization

https://github.com/LiuShiBen/DAFC

공식 코드

Distribution-aware Forgetting Compensation for Exemplar-Free Lifelong Person Re-identification

https://github.com/LoserCheems/OTCE

공식 코드

OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser

https://github.com/MiZhenxing/Switch-NeRF

공식 코드

Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields

https://github.com/Mohd9485/A-OTF

공식 코드

Fast filtering of non-Gaussian models using Amortized Optimal Transport Maps

https://github.com/NVIDIA/NeMo

공식 코드

Llama 3 Meets MoE: Efficient Upcycling

https://github.com/NoemieJaquier/TME

공식 코드

Tensor-variate Mixture of Experts for Proportional Myographic Control of a Robotic Hand

https://github.com/OpenSparseLLMs/CLIP-MoE

공식 코드

CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling

https://github.com/PKU-YuanGroup/LLMBind

공식 코드

LLMBind: A Unified Modality-Task Integration Framework

https://github.com/PKU-YuanGroup/MoE-LLaVA

공식 코드

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models

https://github.com/PaddlePaddle/FleetX

공식 코드

MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services

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