SOTAVerified

Mixture-of-Experts

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1226–1250 of 1312 papers

TitleStatusHype
Condensing Multilingual Knowledge with Lightweight Language-Specific ModulesCode0
Completed Feature Disentanglement Learning for Multimodal MRIs AnalysisCode0
Skeleton-Based Human Action Recognition with Noisy LabelsCode0
UniRestorer: Universal Image Restoration via Adaptively Estimating Image Degradation at Proper GranularityCode0
Manifold-Preserving Transformers are Effective for Short-Long Range EncodingCode0
GEMINUS: Dual-aware Global and Scene-Adaptive Mixture-of-Experts for End-to-End Autonomous DrivingCode0
FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion ModelsCode0
From Knowledge to Noise: CTIM-Rover and the Pitfalls of Episodic Memory in Software Engineering AgentsCode0
A Gaussian Process-based Streaming Algorithm for Prediction of Time Series With Regimes and OutliersCode0
Anomaly Detection by Recombining Gated Unsupervised ExpertsCode0
SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control TasksCode0
Finger Pose Estimation for Under-screen Fingerprint SensorCode0
pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated LearningCode0
FEDKIM: Adaptive Federated Knowledge Injection into Medical Foundation ModelsCode0
m2mKD: Module-to-Module Knowledge Distillation for Modular TransformersCode0
BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-SpoofingCode0
Fast filtering of non-Gaussian models using Amortized Optimal Transport MapsCode0
A Gated Residual Kolmogorov-Arnold Networks for Mixtures of ExpertsCode0
Bidirectional Attention as a Mixture of Continuous Word ExpertsCode0
Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k PolicyCode0
Tight Clusters Make Specialized ExpertsCode0
CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via CompetitionCode0
Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-BackdoorsCode0
LLM-e Guess: Can LLMs Capabilities Advance Without Hardware Progress?Code0
FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language ModelsCode0
Show:102550
← PrevPage 50 of 53Next →

No leaderboard results yet.