{"total":16,"rows":[{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175,"area":"moe"},{"id":"2309.05444","title":"Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning","created":"2023-09-11","cited_by_count":150,"area":"moe"},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113,"area":"moe"},{"id":"2203.06569","title":"SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization","created":"2022-03-13","cited_by_count":61,"area":"moe"},{"id":"2310.09832","title":"Merging Experts into One: Improving Computational Efficiency of Mixture of Experts","created":"2023-10-15","cited_by_count":37,"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":"2310.07188","title":"Adaptive Gating in Mixture-of-Experts based Language Models","created":"2023-10-11","cited_by_count":16,"area":"moe"},{"id":"2207.09094","title":"MoEC: Mixture of Expert Clusters","created":"2022-07-19","cited_by_count":14,"area":"moe"},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2310.15539","title":"SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation","created":"2023-10-24","cited_by_count":9,"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":"2306.05011","title":"Attention Weighted Mixture of Experts with Contrastive Learning for Personalized Ranking in E-commerce","created":"2023-06-08","cited_by_count":3,"area":"moe"},{"id":"2108.07535","title":"SPMoE: Generate Multiple Pattern-Aware Outputs with Sparse Pattern Mixture of Experts","created":"2021-08-17","cited_by_count":0,"area":"moe"},{"id":"2510.27004","title":"Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems","created":"2025-10-30","cited_by_count":0,"area":"moe"},{"id":"2602.18929","title":"Give Users the Wheel: Towards Promptable Recommendation Paradigm","created":"2026-02-21","cited_by_count":0,"area":"moe"},{"id":"2608.31118","title":"When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning","created":"2026-08-31","cited_by_count":0,"area":"moe"}],"next_cursor":null}