{"total":14,"rows":[{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867,"area":"moe"},{"id":"2408.10681","title":"HMoE: Heterogeneous Mixture of Experts for Language Modeling","created":"2024-08-20","cited_by_count":29,"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":"2410.02935","title":"On Expert Estimation in Hierarchical Mixture of Experts: Beyond Softmax Gating Functions","created":"2024-10-03","cited_by_count":16,"area":"moe"},{"id":"2507.11181","title":"Mixture of Experts in Large Language Models","created":"2025-07-15","cited_by_count":15,"area":"moe"},{"id":"2511.10971","title":"ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization","created":"2025-11-14","cited_by_count":7,"area":"moe"},{"id":"2510.10584","title":"Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection","created":"2025-10-12","cited_by_count":5,"area":"moe"},{"id":"2603.00054","title":"Expert Divergence Learning for MoE-based Language Models","created":"2026-02-10","cited_by_count":4,"area":"moe"},{"id":"2602.12556","title":"SD-MoE: Spectral Decomposition for Effective Expert Specialization","created":"2026-02-13","cited_by_count":3,"area":"moe"},{"id":"2406.11919","title":"Graph Knowledge Distillation to Mixture of Experts","created":"2024-06-17","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":"2604.05267","title":"Do Domain-specific Experts exist in MoE-based LLMs?","created":"2026-04-07","cited_by_count":0,"area":"moe"},{"id":"2605.16349","title":"Geometric Asymmetry in MoE Specialization: Functional Decorrelation and Representational Overlap","created":"2026-05-08","cited_by_count":0,"area":"moe"},{"id":"2610.07207","title":"Distributionally Robust Mixture-of-Experts Training","created":"2026-10-05","cited_by_count":0,"area":"moe"}],"next_cursor":null}