{"total":189,"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":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631,"area":"moe"},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867,"area":"moe"},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623,"area":"moe"},{"id":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428,"area":"moe"},{"id":"2201.05596","title":"DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale","created":"2022-01-14","cited_by_count":404,"area":"moe"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"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":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2601.02780","title":"MiMo-V2-Flash Technical Report","created":"2026-01-06","cited_by_count":191,"area":"moe"},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187,"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":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147,"area":"moe"},{"id":"2410.05993","title":"Aria: An Open Multimodal Native Mixture-of-Experts Model","created":"2024-10-08","cited_by_count":138,"area":"moe"},{"id":"2103.13262","title":"FastMoE: A Fast Mixture-of-Expert Training System","created":"2021-03-24","cited_by_count":112,"area":"moe"},{"id":"2210.17223","title":"Accelerating Distributed MoE Training and Inference with Lina","created":"2022-10-31","cited_by_count":109,"area":"moe"},{"id":"2308.12066","title":"Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference","created":"2023-08-23","cited_by_count":104,"area":"moe"},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92,"area":"moe"},{"id":"2109.10465","title":"Scalable and Efficient MoE Training for Multitask Multilingual Models","created":"2021-09-22","cited_by_count":76,"area":"moe"},{"id":"2510.11370","title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","created":"2025-10-13","cited_by_count":72,"area":"moe"},{"id":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60,"area":"moe"},{"id":"2406.06563","title":"Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models","created":"2024-06-03","cited_by_count":59,"area":"moe"},{"id":"2107.11817","title":"Go Wider Instead of Deeper","created":"2021-07-25","cited_by_count":57,"area":"moe"},{"id":"2404.07413","title":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars","created":"2024-04-11","cited_by_count":57,"area":"moe"},{"id":"2410.07348","title":"MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts","created":"2024-10-09","cited_by_count":56,"area":"moe"},{"id":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54,"area":"moe"},{"id":"2501.11873","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","created":"2025-01-21","cited_by_count":54,"area":"moe"},{"id":"2410.07524","title":"Upcycling Large Language Models into Mixture of Experts","created":"2024-10-10","cited_by_count":49,"area":"moe"},{"id":"2502.19811","title":"Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts","created":"2025-02-27","cited_by_count":49,"area":"moe"},{"id":"2105.03036","title":"SpeechMoE: Scaling to Large Acoustic Models with Dynamic Routing Mixture of Experts","created":"2021-05-07","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":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"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":"2205.10034","title":"MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services","created":"2022-05-20","cited_by_count":37,"area":"moe"},{"id":"2402.01771","title":"BlackMamba: Mixture of Experts for State-Space Models","created":"2024-02-01","cited_by_count":37,"area":"moe"},{"id":"2608.30320","title":"On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability","created":"2026-08-31","cited_by_count":35,"area":"moe"},{"id":"2504.02263","title":"MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism","created":"2025-04-03","cited_by_count":32,"area":"moe"},{"id":"2505.11432","title":"MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production","created":"2025-05-16","cited_by_count":31,"area":"moe"},{"id":"2601.08393","title":"Controlled LLM Training on Spectral Sphere","created":"2026-01-13","cited_by_count":31,"area":"moe"},{"id":"2401.08383","title":"Exploiting Inter-Layer Expert Affinity for Accelerating Mixture-of-Experts Model Inference","created":"2024-01-16","cited_by_count":28,"area":"moe"},{"id":"2403.18926","title":"XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection","created":"2024-02-27","cited_by_count":28,"area":"moe"},{"id":"2502.06643","title":"MoETuner: Optimized Mixture of Expert Serving with Balanced Expert Placement and Token Routing","created":"2025-02-10","cited_by_count":26,"area":"moe"},{"id":"2511.00279","title":"LongCat-Flash-Omni Technical Report","created":"2025-10-31","cited_by_count":26,"area":"moe"},{"id":"2305.12129","title":"Lifting the Curse of Capacity Gap in Distilling Language Models","created":"2023-05-20","cited_by_count":25,"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":"2404.19429","title":"Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping","created":"2024-04-30","cited_by_count":22,"area":"moe"},{"id":"2503.05139","title":"Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs","created":"2025-03-07","cited_by_count":22,"area":"moe"},{"id":"2510.24821","title":"Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation","created":"2025-10-28","cited_by_count":22,"area":"moe"},{"id":"2512.14080","title":"SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations","created":"2025-12-16","cited_by_count":21,"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":"2404.02852","title":"Toward Inference-optimal Mixture-of-Expert Large Language Models","created":"2024-04-03","cited_by_count":19,"area":"moe"},{"id":"2411.12364","title":"Ultra-Sparse Memory Network","created":"2024-11-19","cited_by_count":19,"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":"2504.14960","title":"MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core","created":"2025-04-21","cited_by_count":17,"area":"moe"},{"id":"2403.08245","title":"Scattered Mixture-of-Experts Implementation","created":"2024-03-13","cited_by_count":15,"area":"moe"},{"id":"2503.05066","title":"Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts","created":"2025-03-07","cited_by_count":15,"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":"2307.12169","title":"Rail-only: A Low-Cost High-Performance Network for Training LLMs with Trillion Parameters","created":"2023-07-22","cited_by_count":13,"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":"2509.17863","title":"Expert-as-a-Service: Towards Efficient, Scalable, and Robust Large-scale MoE Serving","created":"2025-09-22","cited_by_count":13,"area":"moe"},{"id":"2503.06881","title":"ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration","created":"2025-03-10","cited_by_count":12,"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":"2503.06823","title":"eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference","created":"2025-03-10","cited_by_count":11,"area":"moe"},{"id":"2602.04705","title":"ERNIE 5.0 Technical Report","created":"2026-02-04","cited_by_count":11,"area":"moe"},{"id":"2602.10693","title":"VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training","created":"2026-02-11","cited_by_count":11,"area":"moe"},{"id":"2509.23678","title":"Towards a Comprehensive Scaling Law of Mixture-of-Experts","created":"2025-09-28","cited_by_count":10,"area":"moe"},{"id":"2510.17483","title":"ReXMoE: Reusing Experts with Minimal Overhead in Mixture-of-Experts","created":"2025-10-20","cited_by_count":10,"area":"moe"},{"id":"2507.19017","title":"MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster","created":"2025-07-25","cited_by_count":9,"area":"moe"},{"id":"2601.17111","title":"Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts","created":"2026-01-23","cited_by_count":9,"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":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2410.17043","title":"Optimizing Mixture-of-Experts Inference Time Combining Model Deployment and Communication Scheduling","created":"2024-10-22","cited_by_count":7,"area":"moe"},{"id":"2501.03905","title":"MixNet: A Runtime Reconfigurable Optical-Electrical Fabric for Distributed Mixture-of-Experts Training","created":"2025-01-07","cited_by_count":7,"area":"moe"},{"id":"2508.12851","title":"Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement","created":"2025-08-18","cited_by_count":7,"area":"moe"},{"id":"2509.26520","title":"Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization","created":"2025-09-30","cited_by_count":7,"area":"moe"},{"id":"2410.12247","title":"EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference","created":"2024-10-16","cited_by_count":6,"area":"moe"},{"id":"2412.09952","title":"Llama 3 Meets MoE: Efficient Upcycling","created":"2024-12-13","cited_by_count":6,"area":"moe"},{"id":"2509.25913","title":"Understanding the Mixture-of-Experts with Nadaraya-Watson Kernel","created":"2025-09-30","cited_by_count":6,"area":"moe"},{"id":"2511.06494","title":"Route Experts by Sequence, not by Token","created":"2025-11-09","cited_by_count":6,"area":"moe"},{"id":"2502.16927","title":"BigMac: A Communication-Efficient Mixture-of-Experts Model Structure for Fast Training and Inference","created":"2025-02-24","cited_by_count":5,"area":"moe"},{"id":"2505.20225","title":"FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models","created":"2025-05-26","cited_by_count":5,"area":"moe"},{"id":"2510.03293","title":"From Score Distributions to Balance: Plug-and-Play Mixture-of-Experts Routing","created":"2025-09-29","cited_by_count":5,"area":"moe"},{"id":"2511.17127","title":"Training Foundation Models on a Full-Stack AMD Platform: Compute, Networking, and System Design","created":"2025-11-21","cited_by_count":5,"area":"moe"},{"id":"2602.14159","title":"Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization","created":"2026-02-15","cited_by_count":5,"area":"moe"},{"id":"2603.06626","title":"Grouter: Decoupling Routing from Representation for Accelerated MoE Training","created":"2026-02-22","cited_by_count":5,"area":"moe"},{"id":"2607.18722","title":"Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning","created":"2026-07-21","cited_by_count":5,"area":"moe"},{"id":"2303.08374","title":"MCR-DL: Mix-and-Match Communication Runtime for Deep Learning","created":"2023-03-15","cited_by_count":4,"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":"2408.04307","title":"MoC-System: Efficient Fault Tolerance for Sparse Mixture-of-Experts Model Training","created":"2024-08-08","cited_by_count":4,"area":"moe"},{"id":"2411.10003","title":"Pro-Prophet: A Systematic Load Balancing Method for Efficient Parallel Training of Large-scale MoE Models","created":"2024-11-15","cited_by_count":4,"area":"moe"},{"id":"2506.07366","title":"MoE-GPS: Guidlines for Prediction Strategy for Dynamic Expert Duplication in MoE Load Balancing","created":"2025-06-09","cited_by_count":4,"area":"moe"},{"id":"2507.15465","title":"Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts","created":"2025-07-21","cited_by_count":4,"area":"moe"},{"id":"2507.18671","title":"Innovator: Scientific Continued Pretraining with Fine-grained MoE Upcycling","created":"2025-07-24","cited_by_count":4,"area":"moe"},{"id":"2508.09591","title":"HierMoE: Accelerating MoE Training with Hierarchical Token Deduplication and Expert Swap","created":"2025-08-13","cited_by_count":4,"area":"moe"},{"id":"2512.24157","title":"Training Report of TeleChat3-MoE","created":"2025-12-30","cited_by_count":4,"area":"moe"},{"id":"2605.18643","title":"Post-Trained MoE Can Skip Half Experts via Self-Distillation","created":"2026-05-18","cited_by_count":4,"area":"moe"},{"id":"2606.17952","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","created":"2026-06-16","cited_by_count":4,"area":"moe"},{"id":"2406.00023","title":"Expert-Token Resonance MoE: Bidirectional Routing with Efficiency Affinity-Driven Active Selection","created":"2024-05-24","cited_by_count":3,"area":"moe"},{"id":"2412.15411","title":"Sparse Checkpointing for Fast and Reliable MoE Training","created":"2024-12-19","cited_by_count":3,"area":"moe"}],"next_cursor":"100"}