{"total":14,"rows":[{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623,"area":"moe"},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66,"area":"moe"},{"id":"2507.17702","title":"Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models","created":"2025-07-23","cited_by_count":45,"area":"moe"},{"id":"2403.13358","title":"GeRM: A Generalist Robotic Model with Mixture-of-experts for Quadruped Robot","created":"2024-03-20","cited_by_count":29,"area":"moe"},{"id":"2502.03009","title":"Scaling Laws for Upcycling Mixture-of-Experts Language Models","created":"2025-02-05","cited_by_count":13,"area":"moe"},{"id":"2601.20205","title":"Hyperparameter Transfer with Mixture-of-Expert Layers","created":"2026-01-28","cited_by_count":13,"area":"moe"},{"id":"2411.02115","title":"FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation","created":"2024-11-04","cited_by_count":11,"area":"moe"},{"id":"2407.11030","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","created":"2024-07-03","cited_by_count":10,"area":"moe"},{"id":"2407.00875","title":"MoE-CT: A Novel Approach For Large Language Models Training With Resistance To Catastrophic Forgetting","created":"2024-06-25","cited_by_count":6,"area":"moe"},{"id":"2603.21862","title":"Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization","created":"2026-03-23","cited_by_count":2,"area":"moe"},{"id":"2601.08215","title":"Towards Principled Design of Mixture-of-Experts Language Models under Memory and Inference Constraints","created":"2026-01-13","cited_by_count":0,"area":"moe"},{"id":"2604.09175","title":"Generalization and Scaling Laws for Mixture-of-Experts Transformers","created":"2026-04-10","cited_by_count":0,"area":"moe"},{"id":"2608.10605","title":"Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2609.02204","title":"TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval","created":"2026-09-02","cited_by_count":0,"area":"moe"}],"next_cursor":null}