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/liangjian24/thanora

공식 코드

ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation

https://github.com/liar406/gui-lomo

공식 코드

GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors

https://github.com/lins-lab/dynmoe

공식 코드

Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models

https://github.com/liqs-v2/ctim-rover

공식 코드

From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering Agents

https://github.com/liuhw01/Norface

공식 코드

Norface: Improving Facial Expression Analysis by Identity Normalization

https://github.com/ljaiverson/pfedmoap

공식 코드

Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models

https://github.com/ljcleo/moe-lrc

공식 코드

Not All Models Suit Expert Offloading: On Local Routing Consistency of Mixture-of-Expert Models

https://github.com/lliai/d2moe

공식 코드

Delta Decompression for MoE-based LLMs Compression

https://github.com/llm-random/llm-random

공식 코드

Mixture of Tokens: Continuous MoE through Cross-Example Aggregation

https://github.com/longrongyang/stgc

공식 코드

Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model

https://github.com/losercheems/doge

공식 코드

Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture

https://github.com/losercheems/wonderfulmatrices

공식 코드

Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture

https://github.com/lovesiamesecat/moe-ffd

공식 코드

MoE-FFD: Mixture of Experts for Generalized and Parameter-Efficient Face Forgery Detection

https://github.com/lucky-lance/expert_sparsity

공식 코드

Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models

https://github.com/luodian/sf-moe-dg

공식 코드

Sparse Mixture-of-Experts are Domain Generalizable Learners

https://github.com/lzyfischer/brainmap

공식 코드

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

https://github.com/lzyfischer/graph-mamba

공식 코드

BrainMAP: Learning Multiple Activation Pathways in Brain Networks

https://github.com/makcedward/nlpaug

공식 코드

P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts

https://github.com/maoxiaowei97/dutytte

공식 코드

DutyTTE: Deciphering Uncertainty in Origin-Destination Travel Time Estimation

https://github.com/marcelah/maskedmultimodalvae

공식 코드

Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives

https://github.com/marko-vasic/moet

공식 코드

MoËT: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning

https://github.com/matejmartinc/seke_keyword_extraction

공식 코드

SEKE: Specialised Experts for Keyword Extraction

https://github.com/mateusz-wojcik-97/domain-agnostic-architecture

공식 코드

Domain-Agnostic Neural Architecture for Class Incremental Continual Learning in Document Processing Platform

https://github.com/matthewvowels1/DisentanglingSequences

공식 코드

VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts

https://github.com/mazumder-lab/comet

공식 코드

COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search

https://github.com/mbzuai-oryx/bimedix

공식 코드

BiMediX: Bilingual Medical Mixture of Experts LLM

https://github.com/melonking32/petal

공식 코드

When Parameter-efficient Tuning Meets General-purpose Vision-language Models

https://github.com/metabrainagi/awaker

공식 코드

Awaker2.5-VL: Stably Scaling MLLMs with Parameter-Efficient Mixture of Experts

https://github.com/metaronwang/mego

공식 코드

Learning Mixture-of-Experts for General-Purpose Black-Box Discrete Optimization

https://github.com/mi2datalab/swinsmt

공식 코드

Swin SMT: Global Sequential Modeling in 3D Medical Image Segmentation

https://github.com/michaelzhang01/ISMOE

공식 코드

Embarrassingly Parallel Inference for Gaussian Processes

https://github.com/michaelzhang01/gpmoe

공식 코드

Sequential Gaussian Processes for Online Learning of Nonstationary Functions

https://github.com/microsoft/DeepSpeed

공식 코드

Scalable and Efficient MoE Training for Multitask Multilingual Models

https://github.com/microsoft/Multilingual-Model-Transfer

공식 코드

Multi-Source Cross-Lingual Model Transfer: Learning What to Share

https://github.com/microsoft/Swin-Transformer

공식 코드

Tutel: Adaptive Mixture-of-Experts at Scale

https://github.com/microsoft/automoe

공식 코드

AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation

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