{"total":35,"rows":[{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399,"area":"moe"},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148,"area":"moe"},{"id":"2303.06182","title":"Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference","created":"2023-03-10","cited_by_count":37,"area":"moe"},{"id":"2305.03288","title":"Demystifying Softmax Gating Function in Gaussian Mixture of Experts","created":"2023-05-05","cited_by_count":33,"area":"moe"},{"id":"2111.11831","title":"SpeechMoE2: Mixture-of-Experts Model with Improved Routing","created":"2021-11-23","cited_by_count":26,"area":"moe"},{"id":"2307.05956","title":"Language-Routing Mixture of Experts for Multilingual and Code-Switching Speech Recognition","created":"2023-07-12","cited_by_count":26,"area":"moe"},{"id":"2405.13997","title":"Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts","created":"2024-05-22","cited_by_count":24,"area":"moe"},{"id":"2401.15969","title":"Routers in Vision Mixture of Experts: An Empirical Study","created":"2024-01-29","cited_by_count":23,"area":"moe"},{"id":"2205.14336","title":"Gating Dropout: Communication-efficient Regularization for Sparsely Activated Transformers","created":"2022-05-28","cited_by_count":22,"area":"moe"},{"id":"2305.15663","title":"Mixture-of-Expert Conformer for Streaming Multilingual ASR","created":"2023-05-25","cited_by_count":17,"area":"moe"},{"id":"2501.10714","title":"FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models","created":"2025-01-18","cited_by_count":17,"area":"moe"},{"id":"2112.05820","title":"Building a great multi-lingual teacher with sparsely-gated mixture of experts for speech recognition","created":"2021-12-10","cited_by_count":16,"area":"moe"},{"id":"2405.14131","title":"Statistical Advantages of Perturbing Cosine Router in Mixture of Experts","created":"2024-05-23","cited_by_count":16,"area":"moe"},{"id":"2401.13875","title":"Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?","created":"2024-01-25","cited_by_count":15,"area":"moe"},{"id":"2309.04354","title":"Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts","created":"2023-09-08","cited_by_count":14,"area":"moe"},{"id":"2308.06093","title":"Experts Weights Averaging: A New General Training Scheme for Vision Transformers","created":"2023-08-11","cited_by_count":12,"area":"moe"},{"id":"2503.06823","title":"eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference","created":"2025-03-10","cited_by_count":11,"area":"moe"},{"id":"2306.08586","title":"Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings","created":"2023-06-14","cited_by_count":7,"area":"moe"},{"id":"2309.16178","title":"LAE-ST-MoE: Boosted Language-Aware Encoder Using Speech Translation Auxiliary Task for E2E Code-switching ASR","created":"2023-09-28","cited_by_count":6,"area":"moe"},{"id":"2204.03178","title":"3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition","created":"2022-04-07","cited_by_count":5,"area":"moe"},{"id":"2404.16407","title":"U2++ MoE: Scaling 4.7x parameters with minimal impact on RTF","created":"2024-04-25","cited_by_count":5,"area":"moe"},{"id":"2502.00281","title":"Sigmoid Self-Attention has Lower Sample Complexity than Softmax Self-Attention: A Mixture-of-Experts Perspective","created":"2025-02-01","cited_by_count":4,"area":"moe"},{"id":"2502.10447","title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition","created":"2025-02-11","cited_by_count":4,"area":"moe"},{"id":"2503.03213","title":"Convergence Rates for Softmax Gating Mixture of Experts","created":"2025-03-05","cited_by_count":4,"area":"moe"},{"id":"2507.05724","title":"Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition","created":"2025-07-08","cited_by_count":4,"area":"moe"},{"id":"2209.08326","title":"Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition","created":"2022-09-17","cited_by_count":3,"area":"moe"},{"id":"2510.12744","title":"Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps","created":"2025-10-14","cited_by_count":2,"area":"moe"},{"id":"2412.17507","title":"UME: Upcycling Mixture-of-Experts for Scalable and Efficient Automatic Speech Recognition","created":"2024-12-23","cited_by_count":1,"area":"moe"},{"id":"2505.18455","title":"On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts","created":"2025-05-24","cited_by_count":1,"area":"moe"},{"id":"2602.01967","title":"Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition","created":"2026-02-02","cited_by_count":1,"area":"moe"},{"id":"2310.12236","title":"Direct Neural Machine Translation with Task-level Mixture of Experts models","created":"2023-10-18","cited_by_count":0,"area":"moe"},{"id":"2505.22072","title":"On-the-fly Routing for Zero-shot MoE Speaker Adaptation of Speech Foundation Models for Dysarthric Speech Recognition","created":"2025-05-28","cited_by_count":0,"area":"moe"},{"id":"2509.08470","title":"Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition","created":"2025-09-10","cited_by_count":0,"area":"moe"},{"id":"2602.12546","title":"Decoder-only Conformer with Modality-aware Sparse Mixtures of Experts for ASR","created":"2026-02-13","cited_by_count":0,"area":"moe"},{"id":"2603.00828","title":"MME: Mixture of Mesh Experts with Random Walk Transformer Gating","created":"2026-02-28","cited_by_count":0,"area":"moe"}],"next_cursor":null}