{"total":18,"rows":[{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623,"area":"moe"},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399,"area":"moe"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209,"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":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96,"area":"moe"},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66,"area":"moe"},{"id":"2305.14705","title":"Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models","created":"2023-05-24","cited_by_count":65,"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":"2311.09179","title":"SiRA: Sparse Mixture of Low Rank Adaptation","created":"2023-11-15","cited_by_count":32,"area":"moe"},{"id":"2507.13575","title":"Apple Intelligence Foundation Language Models: Tech Report 2025","created":"2025-07-17","cited_by_count":28,"area":"moe"},{"id":"2105.15082","title":"M6-T: Exploring Sparse Expert Models and Beyond","created":"2021-05-31","cited_by_count":22,"area":"moe"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2602.21798","title":"Excitation: Momentum For Experts","created":"2026-02-25","cited_by_count":0,"area":"moe"},{"id":"2607.19058","title":"Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training","created":"2026-07-21","cited_by_count":0,"area":"moe"},{"id":"2609.04609","title":"CIERA: Cross-Iteration Exponent Reuse for Lossless Allgather in Sharded MoE Training","created":"2026-09-04","cited_by_count":0,"area":"moe"},{"id":"2610.19761","title":"CAST: History-Adaptive Spectral Clipping for LLM Pretraining","created":"2026-10-14","cited_by_count":0,"area":"moe"}],"next_cursor":null}