{"total":27,"rows":[{"id":"2405.01029","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","created":"2024-05-02","cited_by_count":70,"area":"moe"},{"id":"2402.03226","title":"FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion","created":"2024-02-05","cited_by_count":68,"area":"moe"},{"id":"2405.14124","title":"Mixture of Experts Meets Prompt-Based Continual Learning","created":"2024-05-23","cited_by_count":43,"area":"moe"},{"id":"2309.13850","title":"Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts","created":"2023-09-25","cited_by_count":29,"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":"2310.14188","title":"A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts","created":"2023-10-22","cited_by_count":23,"area":"moe"},{"id":"2402.02952","title":"On Least Square Estimation in Softmax Gating Mixture of Experts","created":"2024-02-05","cited_by_count":23,"area":"moe"},{"id":"2305.07572","title":"Towards Convergence Rates for Parameter Estimation in Gaussian-gated Mixture of Experts","created":"2023-05-12","cited_by_count":17,"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":"2502.03044","title":"RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts","created":"2025-02-05","cited_by_count":6,"area":"moe"},{"id":"2403.17404","title":"Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study","created":"2024-03-26","cited_by_count":5,"area":"moe"},{"id":"2501.18936","title":"Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts","created":"2025-01-31","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":"2503.03213","title":"Convergence Rates for Softmax Gating Mixture of Experts","created":"2025-03-05","cited_by_count":4,"area":"moe"},{"id":"2402.05220","title":"On Parameter Estimation in Deviated Gaussian Mixture of Experts","created":"2024-02-07","cited_by_count":2,"area":"moe"},{"id":"2410.13964","title":"Sparse Mixture-of-Experts for Compositional Generalization: Empirical Evidence and Theoretical Foundations of Optimal Sparsity","created":"2024-10-17","cited_by_count":2,"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":"2409.00879","title":"Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts","created":"2024-09-02","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":"2601.14792","title":"Robustness of Mixtures of Experts to Feature Noise","created":"2026-01-21","cited_by_count":1,"area":"moe"},{"id":"2602.01468","title":"A Statistical Theory of Gated Attention through the Lens of Hierarchical Mixture of Experts","created":"2026-02-01","cited_by_count":1,"area":"moe"},{"id":"2605.02124","title":"Soft-to-Hard Routing in Sparse Mixture-of-Experts Models","created":"2026-05-04","cited_by_count":1,"area":"moe"},{"id":"2510.03151","title":"Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective","created":"2025-10-03","cited_by_count":0,"area":"moe"},{"id":"2602.00939","title":"Improving Minimax Estimation Rates for Contaminated Mixture of Multinomial Logistic Experts via Expert Heterogeneity","created":"2026-01-31","cited_by_count":0,"area":"moe"},{"id":"2604.03342","title":"Mixture-of-Experts in Remote Sensing: A Survey","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2609.18842","title":"Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data","created":"2026-09-16","cited_by_count":0,"area":"moe"}],"next_cursor":null}