{"total":278,"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":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"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":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300,"area":"mllm"},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"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":"2108.08284","title":"Stochastic Scene-Aware Motion Prediction","created":"2021-08-18","cited_by_count":203,"area":null},{"id":"2402.03766","title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","created":"2024-02-06","cited_by_count":174,"area":"mllm"},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"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":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2305.18295","title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","created":"2023-05-29","cited_by_count":142,"area":"diffusion"},{"id":"2205.00541","title":"COUCH: Towards Controllable Human-Chair Interactions","created":"2022-05-01","cited_by_count":135,"area":null},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108,"area":"mllm"},{"id":"2302.00883","title":"Synthesizing Physical Character-Scene Interactions","created":"2023-02-02","cited_by_count":104,"area":null},{"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":"2303.07226","title":"Scaling Vision-Language Models with Sparse Mixture of Experts","created":"2023-03-13","cited_by_count":88,"area":"mllm"},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2404.10685","title":"Generating Human Interaction Motions in Scenes with Text Control","created":"2024-04-16","cited_by_count":80,"area":"diffusion"},{"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":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66,"area":"diffusion"},{"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":"2402.13717","title":"Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent","created":"2024-02-21","cited_by_count":52,"area":"agents"},{"id":"2107.11317","title":"Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives","created":"2021-07-23","cited_by_count":50,"area":null},{"id":"2312.08985","title":"OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers","created":"2023-12-14","cited_by_count":47,"area":null},{"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":"2404.10237","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","created":"2024-04-16","cited_by_count":46,"area":"mllm"},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46,"area":null},{"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":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"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":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41,"area":null},{"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":"2105.08489","title":"Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising","created":"2021-05-18","cited_by_count":39,"area":null},{"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":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2106.15434","title":"Zoo-Tuning: Adaptive Transfer from a Zoo of Models","created":"2021-06-29","cited_by_count":35,"area":null},{"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":"2404.09134","title":"Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts Transmission","created":"2024-04-14","cited_by_count":35,"area":"agents"},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"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":"2302.13750","title":"MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition","created":"2023-02-27","cited_by_count":31,"area":null},{"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":"2203.12856","title":"Beyond Fixation: Dynamic Window Visual Transformer","created":"2022-03-24","cited_by_count":28,"area":null},{"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":"2503.05641","title":"Skill-Based Mixture-of-Experts: Adaptive Routing for Heterogeneous Reasoning via Inferred Skills","created":"2025-03-07","cited_by_count":24,"area":"lr"},{"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":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2404.16030","title":"MoDE: CLIP Data Experts via Clustering","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2506.14038","title":"Load Balancing Mixture of Experts with Similarity Preserving Routers","created":"2025-06-16","cited_by_count":22,"area":"moe"},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2106.09563","title":"On Anytime Learning at Macroscale","created":"2021-06-17","cited_by_count":20,"area":null},{"id":"2307.02321","title":"MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers","created":"2023-07-05","cited_by_count":20,"area":null},{"id":"2110.03360","title":"Sparse MoEs meet Efficient Ensembles","created":"2021-10-07","cited_by_count":19,"area":null},{"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":"2208.02894","title":"Redesigning Multi-Scale Neural Network for Crowd Counting","created":"2022-08-04","cited_by_count":17,"area":null},{"id":"2103.15622","title":"Graph Classification by Mixture of Diverse Experts","created":"2021-03-29","cited_by_count":16,"area":null},{"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":"2306.03445","title":"MetaGait: Learning to Learn an Omni Sample Adaptive Representation for Gait Recognition","created":"2023-06-06","cited_by_count":15,"area":null},{"id":"2410.02200","title":"Revisiting Prefix-tuning: Statistical Benefits of Reparameterization among Prompts","created":"2024-10-03","cited_by_count":15,"area":null},{"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":"2302.02609","title":"Improving Domain Generalization with Domain Relations","created":"2023-02-06","cited_by_count":14,"area":null},{"id":"2407.14093","title":"Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models","created":"2024-07-19","cited_by_count":14,"area":"mllm"},{"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":"2405.17082","title":"Ensembling Diffusion Models via Adaptive Feature Aggregation","created":"2024-05-27","cited_by_count":12,"area":"diffusion"}],"next_cursor":"100"}