{"total":30,"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":"2408.04693","title":"Understanding the Performance and Estimating the Cost of LLM Fine-Tuning","created":"2024-08-08","cited_by_count":48,"area":"moe"},{"id":"2303.06318","title":"A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training","created":"2023-03-11","cited_by_count":47,"area":"moe"},{"id":"2002.04013","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","created":"2020-02-10","cited_by_count":43,"area":"moe"},{"id":"2508.02317","title":"VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo","created":"2025-08-04","cited_by_count":20,"area":"moe"},{"id":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2607.07675","title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","created":"2026-07-08","cited_by_count":15,"area":"moe"},{"id":"2505.04519","title":"Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs","created":"2025-05-07","cited_by_count":12,"area":"moe"},{"id":"2606.04101","title":"UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing","created":"2026-06-02","cited_by_count":9,"area":"moe"},{"id":"2504.03871","title":"HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs","created":"2025-04-04","cited_by_count":7,"area":"moe"},{"id":"2304.11414","title":"Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism","created":"2023-04-22","cited_by_count":4,"area":"moe"},{"id":"2405.10951","title":"Block Selective Reprogramming for On-device Training of Vision Transformers","created":"2024-03-25","cited_by_count":4,"area":"moe"},{"id":"2508.12801","title":"Maximum Score Routing For Mixture-of-Experts","created":"2025-08-18","cited_by_count":3,"area":"moe"},{"id":"2508.13337","title":"X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms","created":"2025-08-18","cited_by_count":3,"area":"moe"},{"id":"2509.25689","title":"Collaborative Compression for Large-Scale MoE Deployment on Edge","created":"2025-09-30","cited_by_count":3,"area":"moe"},{"id":"2507.16274","title":"STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training with Spatio-Temporal Planning","created":"2025-07-22","cited_by_count":2,"area":"moe"},{"id":"2408.15305","title":"Parameter-Efficient Quantized Mixture-of-Experts Meets Vision-Language Instruction Tuning for Semiconductor Electron Micrograph Analysis","created":"2024-08-27","cited_by_count":1,"area":"moe"},{"id":"2506.22175","title":"MPipeMoE: Memory Efficient MoE for Pre-trained Models with Adaptive Pipeline Parallelism","created":"2025-06-27","cited_by_count":1,"area":"moe"},{"id":"2508.19078","title":"Federated Fine-Tuning of Sparsely-Activated Large Language Models on Resource-Constrained Devices","created":"2025-08-26","cited_by_count":1,"area":"moe"},{"id":"2511.16947","title":"Fine-grained MoE Load Balancing with Linear Programming","created":"2025-11-21","cited_by_count":1,"area":"moe"},{"id":"2511.21431","title":"MemFine: Memory-Aware Fine-Grained Scheduling for MoE Training","created":"2025-11-26","cited_by_count":1,"area":"moe"},{"id":"2607.01844","title":"Mixture-of-Parallelisms: Towards Memory-Efficient Training Stack for Mixture-of-Experts Models","created":"2026-07-02","cited_by_count":1,"area":"moe"},{"id":"2408.13622","title":"Advancing Enterprise Spatio-Temporal Forecasting Applications: Data Mining Meets Instruction Tuning of Language Models For Multi-modal Time Series Analysis in Low-Resource Settings","created":"2024-08-24","cited_by_count":0,"area":"moe"},{"id":"2512.20920","title":"RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks","created":"2025-12-24","cited_by_count":0,"area":"moe"},{"id":"2604.00785","title":"Scalable Pretraining of Large Mixture of Experts Language Models on Aurora Super Computer","created":"2026-04-01","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":"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":"2609.14306","title":"Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training","created":"2026-09-13","cited_by_count":0,"area":"moe"},{"id":"2610.07333","title":"Memory-Efficient Expert Routing for Distributed MoE Training","created":"2026-10-05","cited_by_count":0,"area":"moe"}],"next_cursor":null}