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/tvseg/dmoe

공식 코드

Distribution-aware Fairness Learning in Medical Image Segmentation From A Control-Theoretic Perspective

https://github.com/tyliupku/nli-debiasing-datasets

공식 코드

An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference

https://github.com/ubc-nlp/mos

공식 코드

Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts

https://github.com/uclaml/MoE

공식 코드

Towards Understanding Mixture of Experts in Deep Learning

https://github.com/umbertocappellazzo/petl_ast

공식 코드

Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters

https://github.com/unites-lab/flex-moe

공식 코드

Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts

https://github.com/unites-lab/mc-smoe

공식 코드

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

https://github.com/unites-lab/moe-quantization

공식 코드

Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark

https://github.com/unites-lab/moe-rbench

공식 코드

$\texttt{MoE-RBench}$: Towards Building Reliable Language Models with Sparse Mixture-of-Experts

https://github.com/unites-lab/occult

공식 코드

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference

https://github.com/vatsal0/default-moe

공식 코드

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts

https://github.com/versestech/cavi-cmn

공식 코드

Gradient-free variational learning with conditional mixture networks

https://github.com/victor7246/transject

공식 코드

Manifold-Preserving Transformers are Effective for Short-Long Range Encoding

https://github.com/victoriagraf/nested_poe

공식 코드

Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors

https://github.com/vinczematyas/SMoSE

공식 코드

SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks

https://github.com/vislearn/esac

공식 코드

Expert Sample Consensus Applied to Camera Re-Localization

https://github.com/vita-group/gnt-move

공식 코드

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts

https://github.com/vita-group/m3vit

공식 코드

M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design

https://github.com/vita-group/random-moe-as-dropout

공식 코드

Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers

https://github.com/vita-group/read-me

공식 코드

Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

https://github.com/vsantjr/dl_blindsr

공식 코드

Deep learning techniques for blind image super-resolution: A high-scale multi-domain perspective evaluation

https://github.com/vsantjr/ideeps

공식 코드

Deep learning techniques for blind image super-resolution: A high-scale multi-domain perspective evaluation

https://github.com/waithz/gw-moe

공식 코드

GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory

https://github.com/wangpuyi/ma-agiqa

공식 코드

Large Multi-modality Model Assisted AI-Generated Image Quality Assessment

https://github.com/wangzrk/LMHaze

공식 코드

LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset

https://github.com/wazenmai/hc-smoe

공식 코드

Retraining-Free Merging of Sparse MoE via Hierarchical Clustering

https://github.com/weikai-li/hierarchicalmoe

공식 코드

Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis

https://github.com/weitianxin/mlp_fusion

공식 코드

MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models

https://github.com/wenruicai/spmtrack

공식 코드

SPMTrack: Spatio-Temporal Parameter-Efficient Fine-Tuning with Mixture of Experts for Scalable Visual Tracking

https://github.com/withinmiaov/a-survey-on-mixture-of-experts

공식 코드

A Survey on Mixture of Experts

https://github.com/wuhy68/parameter-efficient-moe

공식 코드

Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

https://github.com/wuyxin/graphmetro

공식 코드

GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts

https://github.com/xbq1994/meta

공식 코드

Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification

https://github.com/xiangxu-0103/limoe

공식 코드

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

https://github.com/xiongjunguan/draco

공식 코드

Finger Pose Estimation for Under-screen Fingerprint Sensor

https://github.com/xiyan1234567/smetimes

공식 코드

Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs

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