SOTAVerified

Mixture-of-Experts

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1001–1025 of 1312 papers

TitleStatusHype
An Efficient General-Purpose Modular Vision Model via Multi-Task Heterogeneous Training—0
SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills—0
JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving—0
Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings—0
Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce—0
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-ExpertsCode0
Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking—0
Revisiting Hate Speech Benchmarks: From Data Curation to System DeploymentCode0
RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion PathsCode0
Modeling Task Relationships in Multi-variate Soft Sensor with Balanced Mixture-of-Experts—0
Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models—0
Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding—0
Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model—0
Condensing Multilingual Knowledge with Lightweight Language-Specific ModulesCode0
To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis—0
Lifelong Language Pretraining with Distribution-Specialized Experts—0
Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts—0
Locking and Quacking: Stacking Bayesian model predictions by log-pooling and superposition—0
Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception—0
Demystifying Softmax Gating Function in Gaussian Mixture of Experts—0
Steered Mixture-of-Experts Autoencoder Design for Real-Time Image Modelling and Denoising—0
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic CapacityCode0
Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism—0
Revisiting Single-gated Mixtures of Experts—0
FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement—0
Show:102550
← PrevPage 41 of 53Next →

No leaderboard results yet.