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/stefvk/acmoe

공식 코드

Tight Clusters Make Specialized Experts

https://github.com/stephensun11/mxfontpp

공식 코드

MX-Font++: Mixture of Heterogeneous Aggregation Experts for Few-shot Font Generation

https://github.com/stsxxx/finetune

공식 코드

Understanding the Performance and Estimating the Cost of LLM Fine-Tuning

https://github.com/sugarandgugu/GaVaMoE

공식 코드

GaVaMoE: Gaussian-Variational Gated Mixture of Experts for Explainable Recommendation

https://github.com/sunbus100/FreqMoE-main

공식 코드

FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts

https://github.com/sunyuanllm/bip_routing_algorithm

공식 코드

Binary-Integer-Programming Based Algorithm for Expert Load Balancing in Mixture-of-Experts Models

https://github.com/supercomputing-system-ai-lab/milo

공식 코드

MiLo: Efficient Quantized MoE Inference with Mixture of Low-Rank Compensators

https://github.com/supertyd/XTrack

공식 코드

XTrack: Multimodal Training Boosts RGB-X Video Object Trackers

https://github.com/suu990901/CartesianMoE

공식 코드

CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts

https://github.com/suu990901/MaskMoE

공식 코드

MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts

https://github.com/swang-song/ve

공식 코드

VE: Modeling Multivariate Time Series Correlation with Variate Embedding

https://github.com/szc12153/sparse_meta_tuning

공식 코드

Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts

https://github.com/tanganke/pareto_set_learning

공식 코드

Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion

https://github.com/tanganke/weight-ensembling_moe

공식 코드

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts

https://github.com/tannerbohn/AutomaticPullQuoteSelection

공식 코드

Catching Attention with Automatic Pull Quote Selection

https://github.com/tedfoley/nanoGPT

공식 코드

LLM-e Guess: Can LLMs Capabilities Advance Without Hardware Progress?

https://github.com/tencent-ailab/3m-asr

공식 코드

3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition

https://github.com/tencent-ailab/frequency_aug_vae_moesr

공식 코드

Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach

https://github.com/tensorflow/mesh

공식 코드

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

https://github.com/thomassutter/mmvampvae

공식 코드

Unity by Diversity: Improved Representation Learning in Multimodal VAEs

https://github.com/thomassutter/mmvmvae

공식 코드

Unity by Diversity: Improved Representation Learning in Multimodal VAEs

https://github.com/thu-ml/remoe

공식 코드

ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing

https://github.com/thudm/kgtransformer

공식 코드

Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries

https://github.com/thumlp/samoe

공식 코드

Table-based Fact Verification with Self-adaptive Mixture of Experts

https://github.com/thunlp/modularity-analysis

공식 코드

Emergent Modularity in Pre-trained Transformers

https://github.com/tianyi-lab/R2-T2

공식 코드

R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts

https://github.com/tianyi-lab/c3po

공식 코드

C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

https://github.com/tianyi-lab/moe-embedding

공식 코드

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free

https://github.com/tier4/rainfall_modeling_open

공식 코드

Probabilistic Rainfall Estimation from Automotive Lidar

https://github.com/tim-lawson/skip-middle

공식 코드

Learning to Skip the Middle Layers of Transformers

https://github.com/time-moe/time-moe

공식 코드

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

https://github.com/timlee0212/sida-moe

공식 코드

SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models

https://github.com/tomoyi/ewmoe

공식 코드

EWMoE: An effective model for global weather forecasting with mixture-of-experts

https://github.com/tsinghua-mars-lab/statetransformer

공식 코드

Generalizing Motion Planners with Mixture of Experts for Autonomous Driving

https://github.com/tsinghua-msiip/uni-med

공식 코드

Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE

https://github.com/tutujingyugang1/ChatVLA_public

공식 코드

ChatVLA: Unified Multimodal Understanding and Robot Control with Vision-Language-Action Model

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