{"total":67,"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":"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":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"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":"2106.03760","title":"DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning","created":"2021-06-07","cited_by_count":115,"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":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"area":"moe"},{"id":"2411.18466","title":"Complexity Experts are Task-Discriminative Learners for Any Image Restoration","created":"2024-11-27","cited_by_count":77,"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":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"area":"moe"},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42,"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":"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":"2104.09122","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","created":"2021-04-19","cited_by_count":27,"area":"moe"},{"id":"2008.09662","title":"Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations","created":"2020-08-21","cited_by_count":20,"area":"moe"},{"id":"2310.00811","title":"Sparse Backpropagation for MoE Training","created":"2023-10-01","cited_by_count":17,"area":"moe"},{"id":"2409.12136","title":"GRIN: GRadient-INformed MoE","created":"2024-09-18","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":"2211.13491","title":"Spatial Mixture-of-Experts","created":"2022-11-24","cited_by_count":14,"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":"2308.14711","title":"Fast Feedforward Networks","created":"2023-08-28","cited_by_count":11,"area":"moe"},{"id":"2402.12399","title":"Turn Waste into Worth: Rectifying Top-$k$ Router of MoE","created":"2024-02-17","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":"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":"2504.12463","title":"Dense Backpropagation Improves Training for Sparse Mixture-of-Experts","created":"2025-04-16","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":"2402.02933","title":"Intrinsic User-Centric Interpretability through Global Mixture of Experts","created":"2024-02-05","cited_by_count":9,"area":"moe"},{"id":"2212.07571","title":"Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation","created":"2022-12-15","cited_by_count":8,"area":"moe"},{"id":"2506.14646","title":"GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors","created":"2025-06-17","cited_by_count":6,"area":"moe"},{"id":"2503.03213","title":"Convergence Rates for Softmax Gating Mixture of Experts","created":"2025-03-05","cited_by_count":4,"area":"moe"},{"id":"2601.08383","title":"Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models","created":"2026-01-13","cited_by_count":4,"area":"moe"},{"id":"2406.15883","title":"SimSMoE: Solving Representational Collapse via Similarity Measure","created":"2024-06-22","cited_by_count":3,"area":"moe"},{"id":"2410.19504","title":"MoE-Enhanced Explainable Deep Manifold Transformation for Complex Data Embedding and Visualization","created":"2024-10-25","cited_by_count":3,"area":"moe"},{"id":"1909.09192","title":"Learning Sparse Mixture of Experts for Visual Question Answering","created":"2019-09-19","cited_by_count":2,"area":"moe"},{"id":"2306.02824","title":"COMET: Learning Cardinality Constrained Mixture of Experts with Trees and Local Search","created":"2023-06-05","cited_by_count":2,"area":"moe"},{"id":"2510.13079","title":"GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models","created":"2025-10-15","cited_by_count":2,"area":"moe"},{"id":"2512.01750","title":"Multimodal Mixture-of-Experts for ISAC in Low-Altitude Wireless Networks","created":"2025-12-01","cited_by_count":2,"area":"moe"},{"id":"2301.08353","title":"AdaEnsemble: Learning Adaptively Sparse Structured Ensemble Network for Click-Through Rate Prediction","created":"2023-01-06","cited_by_count":1,"area":"moe"},{"id":"2409.14107","title":"Routing in Sparsely-gated Language Models responds to Context","created":"2024-09-21","cited_by_count":1,"area":"moe"},{"id":"2604.23036","title":"Preserving Long-Tailed Expert Information in Mixture-of-Experts Tuning","created":"2026-04-24","cited_by_count":1,"area":"moe"},{"id":"2605.14438","title":"BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE","created":"2026-05-14","cited_by_count":1,"area":"moe"},{"id":"2605.15484","title":"When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing","created":"2026-05-15","cited_by_count":1,"area":"moe"},{"id":"2605.29121","title":"A Minimal Bifurcation Model of Load Imbalance in a Softmax Mixture-of-Experts Router","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2606.01509","title":"ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts","created":"2026-06-01","cited_by_count":1,"area":"moe"},{"id":"2606.01666","title":"DOT-MoE: Differentiable Optimal Transport for MoEfication","created":"2026-06-01","cited_by_count":1,"area":"moe"},{"id":"2410.09687","title":"MoIN: Mixture of Introvert Experts to Upcycle an LLM","created":"2024-10-13","cited_by_count":0,"area":"moe"},{"id":"2503.20750","title":"Optimal Scaling Laws for Efficiency Gains in a Theoretical Transformer-Augmented Sectional MoE Framework","created":"2025-03-26","cited_by_count":0,"area":"moe"},{"id":"2509.15514","title":"MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training","created":"2025-09-19","cited_by_count":0,"area":"moe"},{"id":"2601.13563","title":"ButterflyMoE: Compression-Scalable Ternary Experts via Structured Butterfly Orbits","created":"2026-01-20","cited_by_count":0,"area":"moe"},{"id":"2602.21798","title":"Excitation: Momentum For Experts","created":"2026-02-25","cited_by_count":0,"area":"moe"},{"id":"2603.06746","title":"ButterflyViT: 354$\\times$ Expert Compression for Edge Vision Transformers","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2603.16679","title":"HMAR: Hierarchical Modality-Aware Expert and Dynamic Routing Medical Image Retrieval Architecture","created":"2026-03-17","cited_by_count":0,"area":"moe"},{"id":"2605.00799","title":"GMGaze: MoE-Based Context-Aware Gaze Estimation with CLIP and Multiscale Transformer","created":"2026-05-01","cited_by_count":0,"area":"moe"},{"id":"2605.04952","title":"Adaptive Inverted-Index Routing for Granular Mixtures-of-Experts","created":"2026-05-06","cited_by_count":0,"area":"moe"},{"id":"2605.13247","title":"EMO: Frustratingly Easy Progressive Training of Extendable MoE","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2607.06601","title":"TriRoute: Unified Learned Routing for Joint Adaptive Attention, Experts, and KV-Cache Allocation","created":"2026-07-07","cited_by_count":0,"area":"moe"},{"id":"2607.22577","title":"cMoLLM at Scale: Horizontal Scaling Laws for Mixture-of-LLMs","created":"2026-06-06","cited_by_count":0,"area":"moe"},{"id":"2609.00284","title":"WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network Optimization","created":"2026-08-31","cited_by_count":0,"area":"moe"},{"id":"2609.18842","title":"Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.34077","title":"MaskCoFT: Masked Co-Adaptive Fine-Tuning for Memory-Efficient MoE Inference","created":"2026-09-28","cited_by_count":0,"area":"moe"},{"id":"2610.02241","title":"Hardware-Native Joint Sparse-Quantization for Trillion-Scale Mixture-of-Experts","created":"2026-09-29","cited_by_count":0,"area":"moe"},{"id":"2610.19232","title":"Spectral-MoE: Heterogeneous Per-Layer Expert Utilization in Dense-to-MoE Conversion","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}