{"total":225,"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":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747,"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":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399,"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":"2212.05055","title":"Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints","created":"2022-12-09","cited_by_count":209,"area":"moe"},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203,"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":"2204.09179","title":"On the Representation Collapse of Sparse Mixture of Experts","created":"2022-04-20","cited_by_count":157,"area":"moe"},{"id":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"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":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148,"area":"moe"},{"id":"2406.16554","title":"LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training","created":"2024-06-24","cited_by_count":123,"area":"moe"},{"id":"2109.04290","title":"Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss","created":"2021-09-09","cited_by_count":116,"area":"moe"},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113,"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":"2310.18339","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","created":"2023-10-21","cited_by_count":111,"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":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108,"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":"2204.08396","title":"StableMoE: Stable Routing Strategy for Mixture of Experts","created":"2022-04-18","cited_by_count":100,"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":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"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":"2206.00277","title":"Task-Specific Expert Pruning for Sparse Mixture-of-Experts","created":"2022-06-01","cited_by_count":72,"area":"moe"},{"id":"2410.08245","title":"Flex-MoE: Modeling Arbitrary Modality Combination via the Flexible Mixture-of-Experts","created":"2024-10-10","cited_by_count":70,"area":"moe"},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66,"area":"moe"},{"id":"2410.12013","title":"MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Router","created":"2024-10-15","cited_by_count":62,"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":"2210.05144","title":"Mixture of Attention Heads: Selecting Attention Heads Per Token","created":"2022-10-11","cited_by_count":60,"area":"moe"},{"id":"2303.01610","title":"Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers","created":"2023-03-02","cited_by_count":59,"area":"moe"},{"id":"2405.16039","title":"MoEUT: Mixture-of-Experts Universal Transformers","created":"2024-05-25","cited_by_count":59,"area":"moe"},{"id":"2206.04674","title":"Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs","created":"2022-06-09","cited_by_count":58,"area":"moe"},{"id":"2107.11817","title":"Go Wider Instead of Deeper","created":"2021-07-25","cited_by_count":57,"area":"moe"},{"id":"2405.14297","title":"Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models","created":"2024-05-23","cited_by_count":56,"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":"2304.03946","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","created":"2023-04-08","cited_by_count":53,"area":"moe"},{"id":"2208.02813","title":"Towards Understanding Mixture of Experts in Deep Learning","created":"2022-08-04","cited_by_count":52,"area":"moe"},{"id":"2204.07689","title":"Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners","created":"2022-04-16","cited_by_count":51,"area":"moe"},{"id":"2501.12370","title":"Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models","created":"2025-01-21","cited_by_count":50,"area":"moe"},{"id":"2502.00806","title":"UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs","created":"2025-02-02","cited_by_count":49,"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":"2208.07638","title":"Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries","created":"2022-08-16","cited_by_count":39,"area":"moe"},{"id":"2204.07675","title":"MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation","created":"2022-04-15","cited_by_count":37,"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":"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":"2203.14685","title":"HetuMoE: An Efficient Trillion-scale Mixture-of-Expert Distributed Training System","created":"2022-03-28","cited_by_count":36,"area":"moe"},{"id":"2510.08396","title":"FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts","created":"2025-10-09","cited_by_count":35,"area":"moe"},{"id":"2106.02318","title":"AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding","created":"2021-06-04","cited_by_count":32,"area":"moe"},{"id":"2408.10159","title":"Customizing Language Models with Instance-wise LoRA for Sequential Recommendation","created":"2024-08-19","cited_by_count":32,"area":"moe"},{"id":"2203.01104","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","created":"2022-03-02","cited_by_count":31,"area":"moe"},{"id":"2112.14397","title":"EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate","created":"2021-12-29","cited_by_count":30,"area":"moe"},{"id":"2310.09762","title":"Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer","created":"2023-10-15","cited_by_count":29,"area":"moe"},{"id":"2201.10890","title":"One Student Knows All Experts Know: From Sparse to Dense","created":"2022-01-26","cited_by_count":25,"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":"2210.16433","title":"Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models","created":"2022-10-28","cited_by_count":24,"area":"moe"},{"id":"2305.18691","title":"Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts","created":"2023-05-30","cited_by_count":23,"area":"moe"},{"id":"2105.06597","title":"RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling","created":"2021-05-14","cited_by_count":22,"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":"2110.07280","title":"P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts","created":"2021-10-14","cited_by_count":22,"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":"2308.09723","title":"FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs","created":"2023-08-16","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":"2401.13920","title":"LocMoE: A Low-Overhead MoE for Large Language Model Training","created":"2024-01-25","cited_by_count":19,"area":"moe"},{"id":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18,"area":"moe"},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2310.00811","title":"Sparse Backpropagation for MoE Training","created":"2023-10-01","cited_by_count":17,"area":"moe"},{"id":"2507.23279","title":"Unveiling Super Experts in Mixture-of-Experts Large Language Models","created":"2025-07-31","cited_by_count":17,"area":"moe"},{"id":"2310.04361","title":"Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion","created":"2023-10-06","cited_by_count":16,"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":"2402.05382","title":"Task-customized Masked AutoEncoder via Mixture of Cluster-conditional Experts","created":"2024-02-08","cited_by_count":16,"area":"moe"},{"id":"2408.05430","title":"HoME: Hierarchy of Multi-Gate Experts for Multi-Task Learning at Kuaishou","created":"2024-08-10","cited_by_count":16,"area":"moe"},{"id":"2302.09915","title":"TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training","created":"2023-02-20","cited_by_count":15,"area":"moe"},{"id":"2409.06669","title":"DA-MoE: Towards Dynamic Expert Allocation for Mixture-of-Experts Models","created":"2024-09-10","cited_by_count":15,"area":"moe"},{"id":"2501.14269","title":"Hierarchical Time-Aware Mixture of Experts for Multi-Modal Sequential Recommendation","created":"2025-01-24","cited_by_count":15,"area":"moe"},{"id":"2601.18699","title":"Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2026-01-26","cited_by_count":14,"area":"moe"},{"id":"2503.11880","title":"FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA","created":"2025-03-14","cited_by_count":13,"area":"moe"},{"id":"2205.12399","title":"Sparse Mixers: Combining MoE and Mixing to build a more efficient BERT","created":"2022-05-24","cited_by_count":12,"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":"2411.06681","title":"WDMoE: Wireless Distributed Mixture of Experts for Large Language Models","created":"2024-11-11","cited_by_count":12,"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":"2206.12845","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","created":"2022-06-26","cited_by_count":11,"area":"moe"},{"id":"2308.14711","title":"Fast Feedforward Networks","created":"2023-08-28","cited_by_count":11,"area":"moe"},{"id":"2404.19192","title":"Mix of Experts Language Model for Named Entity Recognition","created":"2024-04-30","cited_by_count":11,"area":"moe"},{"id":"2405.18832","title":"MoNDE: Mixture of Near-Data Experts for Large-Scale Sparse Models","created":"2024-05-29","cited_by_count":11,"area":"moe"},{"id":"2411.18322","title":"Mixture of Experts in Image Classification: What's the Sweet Spot?","created":"2024-11-27","cited_by_count":11,"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":"2210.07535","title":"AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation","created":"2022-10-14","cited_by_count":10,"area":"moe"},{"id":"2306.00434","title":"Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking","created":"2023-06-01","cited_by_count":10,"area":"moe"},{"id":"2501.15316","title":"ToMoE: Converting Dense Large Language Models to Mixture-of-Experts through Dynamic Structural Pruning","created":"2025-01-25","cited_by_count":10,"area":"moe"},{"id":"2502.13577","title":"Unraveling the Localized Latents: Learning Stratified Manifold Structures in LLM Embedding Space with Sparse Mixture-of-Experts","created":"2025-02-19","cited_by_count":10,"area":"moe"},{"id":"2508.02853","title":"Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives","created":"2025-08-04","cited_by_count":10,"area":"moe"},{"id":"2510.05245","title":"Stratum: System-Hardware Co-Design with Tiered Monolithic 3D-Stackable DRAM for Efficient MoE Serving","created":"2025-10-06","cited_by_count":10,"area":"moe"},{"id":"2207.01145","title":"Memory Population in Continual Learning via Outlier Elimination","created":"2022-07-04","cited_by_count":9,"area":"moe"},{"id":"2211.05528","title":"PAD-Net: An Efficient Framework for Dynamic Networks","created":"2022-11-10","cited_by_count":9,"area":"moe"},{"id":"2305.13999","title":"Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model","created":"2023-05-23","cited_by_count":9,"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"}],"next_cursor":"100"}