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/RLHFlow/RLHF-Reward-Modeling

공식 코드

Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts

https://github.com/SStarCCat/HM4SR

공식 코드

Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation

https://github.com/ShayekhBinIslam/openrag

공식 코드

Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Models

https://github.com/SijinKim/mepsnet

공식 코드

Restoring Spatially-Heterogeneous Distortions using Mixture of Experts Network

https://github.com/TUDB-Labs/MixLoRA

공식 코드

MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts

https://github.com/Tharun24/MACH

공식 코드

Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Products

https://github.com/Trung-TinNGUYEN/NamsGLoME-Simulation

공식 코드

A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models

https://github.com/Tsingularity/youtube-8m

공식 코드

Hierarchical Deep Recurrent Architecture for Video Understanding

https://github.com/TsungWeiTsai/MiCE

공식 코드

MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering

https://github.com/WangRongsheng/Aurora

공식 코드

Aurora:Activating Chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning

https://github.com/XiaochenWang-PSU/FedKIM

공식 코드

FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation Models

https://github.com/aaronhuang-778/mc-moe

공식 코드

MC-MoE: Mixture Compressor for Mixture-of-Experts LLMs Gains More

https://github.com/ablustrund/loramoe

공식 코드

LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin

https://github.com/adlith/moe-jetpack

공식 코드

MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks

https://github.com/advhscmoe/adv_hsc_moe

공식 코드

Adversarial Mixture Of Experts with Category Hierarchy Soft Constraint

https://github.com/agostini335/mmvmvae-mimic

공식 코드

Unity by Diversity: Improved Representation Learning in Multimodal VAEs

https://github.com/ai-explorer-123/gusd

공식 코드

Unveiling the Hidden: Movie Genre and User Bias in Spoiler Detection

https://github.com/ai4co/awesome-fm4co

공식 코드

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts

https://github.com/aidc-ai/parrot

공식 코드

Parrot: Multilingual Visual Instruction Tuning

https://github.com/akalikong/ilora

공식 코드

Customizing Language Models with Instance-wise LoRA for Sequential Recommendation

https://github.com/alexhe101/fame-net

공식 코드

Frequency-Adaptive Pan-Sharpening with Mixture of Experts

https://github.com/alg-znsy-li/mofe-time

공식 코드

MoFE-Time: Mixture of Frequency Domain Experts for Time-Series Forecasting Models

https://github.com/allenai/OLMoE

공식 코드

OLMoE: Open Mixture-of-Experts Language Models

https://github.com/alper111/hmog

공식 코드

Hierarchical Mixtures of Generators for Adversarial Learning

https://github.com/alrhub/imc

공식 코드

Information Maximizing Curriculum: A Curriculum-Based Approach for Imitating Diverse Skills

https://github.com/amazon-science/eideticnet-training

공식 코드

Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting

https://github.com/ami-iit/paper_guo_2023_humanoids_lifting_risk_prediction

공식 코드

Online Action Recognition for Human Risk Prediction with Anticipated Haptic Alert via Wearables

https://github.com/amudide/switch_sae

공식 코드

Efficient Dictionary Learning with Switch Sparse Autoencoders

https://github.com/andkopf/MoESimVAE

공식 코드

Mixture-of-Experts Variational Autoencoder for Clustering and Generating from Similarity-Based Representations on Single Cell Data

https://github.com/andpotap/einsum-search

공식 코드

Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices

https://github.com/andreascharalamp/fastfeedforward-experiments

공식 코드

Enhancing Fast Feed Forward Networks with Load Balancing and a Master Leaf Node

https://github.com/apple/axlearn

공식 코드

Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training

https://github.com/applied-machine-learning-lab/m3oe

공식 코드

M3oE: Multi-Domain Multi-Task Mixture-of Experts Recommendation Framework

https://github.com/ask-berkeley/physics-nns-hard-constraints

공식 코드

Scaling physics-informed hard constraints with mixture-of-experts

https://github.com/avinabsaha/ReIQA

공식 코드

Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild

https://github.com/bartwojcik/d2dmoe

공식 코드

Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion

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