{"total":19,"rows":[{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073,"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":"2211.15841","title":"MegaBlocks: Efficient Sparse Training with Mixture-of-Experts","created":"2022-11-29","cited_by_count":209,"area":"moe"},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175,"area":"moe"},{"id":"2601.22101","title":"ECO: Quantized Training without Full-Precision Master Weights","created":"2026-01-29","cited_by_count":5,"area":"moe"},{"id":"2512.24157","title":"Training Report of TeleChat3-MoE","created":"2025-12-30","cited_by_count":4,"area":"moe"},{"id":"2510.08008","title":"Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts","created":"2025-10-09","cited_by_count":1,"area":"moe"},{"id":"2511.02302","title":"FP8-Flow-MoE: A Casting-Free FP8 Recipe without Double Quantization Error","created":"2025-11-04","cited_by_count":1,"area":"moe"},{"id":"2607.19539","title":"Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts","created":"2026-07-21","cited_by_count":1,"area":"moe"},{"id":"2510.20111","title":"AsyncHZP: Hierarchical ZeRO Parallelism with Asynchronous Scheduling for Scalable LLM Training","created":"2025-10-23","cited_by_count":0,"area":"moe"},{"id":"2602.11543","title":"Pretraining A Large Language Model using Distributed GPUs: A Memory-Efficient Decentralized Paradigm","created":"2026-02-12","cited_by_count":0,"area":"moe"},{"id":"2605.04058","title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","created":"2026-04-10","cited_by_count":0,"area":"moe"},{"id":"2605.26842","title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training","created":"2026-05-26","cited_by_count":0,"area":"moe"},{"id":"2606.19025","title":"FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs","created":"2026-06-17","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":"2609.16179","title":"Z-Loss Backward Geometry in Dense Output Heads and Sparse Routers","created":"2026-07-31","cited_by_count":0,"area":"moe"},{"id":"2610.05109","title":"LoopMoEVR: Loop-Based Degradation-Aware Mixture-of-Experts for Unified UHD Video Restoration","created":"2026-10-04","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}