{"total":137,"rows":[{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509,"area":"moe"},{"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":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747,"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":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"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":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98,"area":"moe"},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91,"area":"moe"},{"id":"2405.01029","title":"MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts","created":"2024-05-02","cited_by_count":70,"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":"2305.14705","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":"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":"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":"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":"2411.01433","title":"HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference","created":"2024-11-03","cited_by_count":55,"area":"moe"},{"id":"2406.16437","title":"Theory on Mixture-of-Experts in Continual Learning","created":"2024-06-24","cited_by_count":54,"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":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45,"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":"2405.14124","title":"Mixture of Experts Meets Prompt-Based Continual Learning","created":"2024-05-23","cited_by_count":43,"area":"moe"},{"id":"2404.05089","title":"SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts","created":"2024-04-07","cited_by_count":40,"area":"moe"},{"id":"1907.04377","title":"Convergence Rates for Gaussian Mixtures of Experts","created":"2019-07-09","cited_by_count":39,"area":"moe"},{"id":"2204.09636","title":"Residual Mixture of Experts","created":"2022-04-20","cited_by_count":39,"area":"moe"},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35,"area":"moe"},{"id":"2505.03804","title":"MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance","created":"2025-05-02","cited_by_count":34,"area":"moe"},{"id":"2305.03288","title":"Demystifying Softmax Gating Function in Gaussian Mixture of Experts","created":"2023-05-05","cited_by_count":33,"area":"moe"},{"id":"2109.05238","title":"Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy","created":"2021-09-11","cited_by_count":32,"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":"2308.10110","title":"Robust Mixture-of-Expert Training for Convolutional Neural Networks","created":"2023-08-19","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":"2210.10253","title":"On the Adversarial Robustness of Mixture of Experts","created":"2022-10-19","cited_by_count":28,"area":"moe"},{"id":"2402.12550","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","created":"2024-02-19","cited_by_count":28,"area":"moe"},{"id":"2308.11793","title":"Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts","created":"2023-08-22","cited_by_count":27,"area":"moe"},{"id":"2502.19261","title":"Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization","created":"2025-02-26","cited_by_count":24,"area":"moe"},{"id":"2401.15969","title":"Routers in Vision Mixture of Experts: An Empirical Study","created":"2024-01-29","cited_by_count":23,"area":"moe"},{"id":"2402.02526","title":"CompeteSMoE -- Effective Training of Sparse Mixture of Experts via Competition","created":"2024-02-04","cited_by_count":23,"area":"moe"},{"id":"2506.14038","title":"Load Balancing Mixture of Experts with Similarity Preserving Routers","created":"2025-06-16","cited_by_count":22,"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":"2403.02600","title":"TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts","created":"2024-03-05","cited_by_count":18,"area":"moe"},{"id":"2206.02107","title":"Interpretable Mixture of Experts","created":"2022-06-05","cited_by_count":17,"area":"moe"},{"id":"2407.00256","title":"One Prompt is not Enough: Automated Construction of a Mixture-of-Expert Prompts","created":"2024-06-28","cited_by_count":16,"area":"moe"},{"id":"2410.10456","title":"Ada-K Routing: Boosting the Efficiency of MoE-based LLMs","created":"2024-10-14","cited_by_count":16,"area":"moe"},{"id":"2507.11181","title":"Mixture of Experts in Large Language Models","created":"2025-07-15","cited_by_count":15,"area":"moe"},{"id":"2204.10598","title":"Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability","created":"2022-04-22","cited_by_count":14,"area":"moe"},{"id":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"area":"moe"},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14,"area":"moe"},{"id":"2309.03904","title":"Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis","created":"2023-09-07","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":"2204.08753","title":"Table-based Fact Verification with Self-adaptive Mixture of Experts","created":"2022-04-19","cited_by_count":12,"area":"moe"},{"id":"2402.00893","title":"MoDE: A Mixture-of-Experts Model with Mutual Distillation among the Experts","created":"2024-01-31","cited_by_count":12,"area":"moe"},{"id":"2411.00782","title":"TradExpert: Revolutionizing Trading with Mixture of Expert LLMs","created":"2024-10-16","cited_by_count":12,"area":"moe"},{"id":"2503.15798","title":"Mixture of Lookup Experts","created":"2025-03-20","cited_by_count":12,"area":"moe"},{"id":"2303.06095","title":"HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction","created":"2023-03-10","cited_by_count":11,"area":"moe"},{"id":"2109.11817","title":"Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts","created":"2021-09-24","cited_by_count":10,"area":"moe"},{"id":"2304.05497","title":"Revisiting Single-gated Mixtures of Experts","created":"2023-04-11","cited_by_count":10,"area":"moe"},{"id":"2405.16486","title":"Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation","created":"2024-05-26","cited_by_count":10,"area":"moe"},{"id":"2503.23100","title":"MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models","created":"2025-03-29","cited_by_count":10,"area":"moe"},{"id":"2506.21103","title":"Learning to Skip the Middle Layers of Transformers","created":"2025-06-26","cited_by_count":10,"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":"2405.19086","title":"MEMoE: Enhancing Model Editing with Mixture of Experts Adaptors","created":"2024-05-29","cited_by_count":9,"area":"moe"},{"id":"2411.08212","title":"PERFT: Parameter-Efficient Routed Fine-Tuning for Mixture-of-Expert Model","created":"2024-11-12","cited_by_count":9,"area":"moe"},{"id":"2505.06839","title":"The power of fine-grained experts: Granularity boosts expressivity in Mixture of Experts","created":"2025-05-11","cited_by_count":9,"area":"moe"},{"id":"2508.02587","title":"Parameter-Efficient Routed Fine-Tuning: Mixture-of-Experts Demands Mixture of Adaptation Modules","created":"2025-08-04","cited_by_count":8,"area":"moe"},{"id":"2402.06512","title":"Multimodal Clinical Trial Outcome Prediction with Large Language Models","created":"2024-02-09","cited_by_count":7,"area":"moe"},{"id":"2403.13468","title":"DESIRE-ME: Domain-Enhanced Supervised Information REtrieval using Mixture-of-Experts","created":"2024-03-20","cited_by_count":7,"area":"moe"},{"id":"2007.12349","title":"Adversarial Mixture Of Experts with Category Hierarchy Soft Constraint","created":"2020-07-24","cited_by_count":6,"area":"moe"},{"id":"2103.07292","title":"VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts","created":"2021-03-12","cited_by_count":6,"area":"moe"},{"id":"2401.14426","title":"M$^3$TN: Multi-gate Mixture-of-Experts based Multi-valued Treatment Network for Uplift Modeling","created":"2024-01-24","cited_by_count":6,"area":"moe"},{"id":"2406.03637","title":"Style Mixture of Experts for Expressive Text-To-Speech Synthesis","created":"2024-06-05","cited_by_count":6,"area":"moe"},{"id":"2411.00918","title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","created":"2024-11-01","cited_by_count":6,"area":"moe"},{"id":"2502.03044","title":"RepLoRA: Reparameterizing Low-Rank Adaptation via the Perspective of Mixture of Experts","created":"2025-02-05","cited_by_count":6,"area":"moe"},{"id":"2504.01337","title":"Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design","created":"2025-04-02","cited_by_count":6,"area":"moe"},{"id":"2508.06318","title":"Mixture of Experts Guided by Gaussian Splatters Matters: A new Approach to Weakly-Supervised Video Anomaly Detection","created":"2025-08-08","cited_by_count":6,"area":"moe"},{"id":"1910.09450","title":"Tree-gated Deep Mixture-of-Experts For Pose-robust Face Alignment","created":"2019-10-21","cited_by_count":5,"area":"moe"},{"id":"2310.15961","title":"Mixture of Tokens: Continuous MoE through Cross-Example Aggregation","created":"2023-10-24","cited_by_count":5,"area":"moe"},{"id":"2312.16610","title":"Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation","created":"2023-12-27","cited_by_count":5,"area":"moe"},{"id":"2403.17404","title":"Generalization Error Analysis for Sparse Mixture-of-Experts: A Preliminary Study","created":"2024-03-26","cited_by_count":5,"area":"moe"},{"id":"2405.00568","title":"Powering In-Database Dynamic Model Slicing for Structured Data Analytics","created":"2024-05-01","cited_by_count":5,"area":"moe"},{"id":"2409.12370","title":"Robust Audiovisual Speech Recognition Models with Mixture-of-Experts","created":"2024-09-19","cited_by_count":5,"area":"moe"},{"id":"2410.16077","title":"CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts","created":"2024-10-21","cited_by_count":5,"area":"moe"},{"id":"2412.15690","title":"Theory of Mixture-of-Experts for Mobile Edge Computing","created":"2024-12-20","cited_by_count":5,"area":"moe"},{"id":"2501.18936","title":"Revisit Visual Prompt Tuning: The Expressiveness of Prompt Experts","created":"2025-01-31","cited_by_count":5,"area":"moe"},{"id":"2509.00996","title":"MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper","created":"2025-08-31","cited_by_count":5,"area":"moe"},{"id":"1703.09302","title":"Speech Enhancement using a Deep Mixture of Experts","created":"2017-03-27","cited_by_count":4,"area":"moe"},{"id":"2312.01361","title":"MoEC: Mixture of Experts Implicit Neural Compression","created":"2023-12-03","cited_by_count":4,"area":"moe"},{"id":"2408.16429","title":"Gradient-free variational learning with conditional mixture networks","created":"2024-08-29","cited_by_count":4,"area":"moe"},{"id":"2412.11864","title":"Investigating Mixture of Experts in Dense Retrieval","created":"2024-12-16","cited_by_count":4,"area":"moe"},{"id":"2501.03432","title":"Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection","created":"2025-01-06","cited_by_count":4,"area":"moe"},{"id":"2509.05086","title":"Robust Experts: the Effect of Adversarial Training on CNNs with Sparse Mixture-of-Experts Layers","created":"2025-09-05","cited_by_count":4,"area":"moe"},{"id":"2511.01463","title":"HMVLM: Human Motion-Vision-Lanuage Model via MoE LoRA","created":"2025-11-03","cited_by_count":4,"area":"moe"},{"id":"2511.13760","title":"MoETTA: Test-Time Adaptation Under Mixed Distribution Shifts with MoE-LayerNorm","created":"2025-11-14","cited_by_count":4,"area":"moe"},{"id":"2503.20633","title":"Enhancing Multi-modal Models with Heterogeneous MoE Adapters for Fine-tuning","created":"2025-03-26","cited_by_count":3,"area":"moe"},{"id":"2505.15414","title":"Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks","created":"2025-05-21","cited_by_count":3,"area":"moe"},{"id":"2508.09204","title":"MoQE: Improve Quantization Model performance via Mixture of Quantization Experts","created":"2025-08-09","cited_by_count":3,"area":"moe"},{"id":"2508.12801","title":"Maximum Score Routing For Mixture-of-Experts","created":"2025-08-18","cited_by_count":3,"area":"moe"},{"id":"2402.05220","title":"On Parameter Estimation in Deviated Gaussian Mixture of Experts","created":"2024-02-07","cited_by_count":2,"area":"moe"}],"next_cursor":"100"}