{"total":100,"rows":[{"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":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205,"area":"inference"},{"id":"2204.09179","title":"On the Representation Collapse of Sparse Mixture of Experts","created":"2022-04-20","cited_by_count":157,"area":"moe"},{"id":"2507.10524","title":"Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation","created":"2025-07-14","cited_by_count":133,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"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":"2510.11370","title":"Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers","created":"2025-10-13","cited_by_count":72,"area":"moe"},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66,"area":"diffusion"},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"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":"2407.00945","title":"Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs","created":"2024-07-01","cited_by_count":53,"area":"moe"},{"id":"2406.18219","title":"A Closer Look into Mixture-of-Experts in Large Language Models","created":"2024-06-26","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":"2404.05019","title":"Shortcut-connected Expert Parallelism for Accelerating Mixture-of-Experts","created":"2024-04-07","cited_by_count":32,"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":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2402.12656","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","created":"2024-02-20","cited_by_count":26,"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":"2401.02731","title":"Parameter-Efficient Sparsity Crafting from Dense to Mixture-of-Experts for Instruction Tuning on General Tasks","created":"2024-01-05","cited_by_count":22,"area":"moe"},{"id":"2212.10551","title":"Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation","created":"2022-12-20","cited_by_count":21,"area":null},{"id":"2408.06793","title":"Layerwise Recurrent Router for Mixture-of-Experts","created":"2024-08-13","cited_by_count":21,"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":"2501.10714","title":"FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models","created":"2025-01-18","cited_by_count":17,"area":"moe"},{"id":"2208.11290","title":"ADMoE: Anomaly Detection with Mixture-of-Experts from Noisy Labels","created":"2022-08-24","cited_by_count":15,"area":"moe"},{"id":"2207.09094","title":"MoEC: Mixture of Expert Clusters","created":"2022-07-19","cited_by_count":14,"area":"moe"},{"id":"2411.18797","title":"SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?","created":"2024-11-27","cited_by_count":14,"area":"moe"},{"id":"2508.19594","title":"Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMs","created":"2025-08-27","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":"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":"2312.03464","title":"Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2410.14574","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","created":"2024-10-18","cited_by_count":9,"area":"moe"},{"id":"2605.07260","title":"When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models","created":"2026-05-08","cited_by_count":9,"area":"moe"},{"id":"2211.08253","title":"HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization","created":"2022-11-15","cited_by_count":8,"area":"moe"},{"id":"2408.11869","title":"ELDER: Enhancing Lifelong Model Editing with Mixture-of-LoRA","created":"2024-08-19","cited_by_count":8,"area":null},{"id":"2409.01483","title":"Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning","created":"2024-09-02","cited_by_count":8,"area":"moe"},{"id":"2502.15315","title":"Tight Clusters Make Specialized Experts","created":"2025-02-21","cited_by_count":8,"area":"moe"},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2511.10971","title":"ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization","created":"2025-11-14","cited_by_count":7,"area":"moe"},{"id":"2308.03275","title":"Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization","created":"2023-08-07","cited_by_count":6,"area":"distill"},{"id":"2312.10193","title":"Adaptive Computation Modules: Granular Conditional Computation For Efficient Inference","created":"2023-12-15","cited_by_count":6,"area":null},{"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":"2510.23027","title":"Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts","created":"2025-10-27","cited_by_count":6,"area":"lr"},{"id":"2511.06494","title":"Route Experts by Sequence, not by Token","created":"2025-11-09","cited_by_count":6,"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":"2502.18821","title":"CAMEx: Curvature-aware Merging of Experts","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2510.05213","title":"VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2603.06626","title":"Grouter: Decoupling Routing from Representation for Accelerated MoE Training","created":"2026-02-22","cited_by_count":5,"area":"moe"},{"id":"2605.15403","title":"$\\phi$-Balancing for Mixture-of-Experts Training","created":"2026-05-14","cited_by_count":5,"area":"moe"},{"id":"2411.19402","title":"On the Role of Discrete Representation in Sparse Mixture of Experts","created":"2024-11-28","cited_by_count":4,"area":"moe"},{"id":"2502.10447","title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition","created":"2025-02-11","cited_by_count":4,"area":"moe"},{"id":"2505.00792","title":"Improving Routing in Sparse Mixture of Experts with Graph of Tokens","created":"2025-05-01","cited_by_count":4,"area":"moe"},{"id":"2507.05724","title":"Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition","created":"2025-07-08","cited_by_count":4,"area":"moe"},{"id":"2510.13451","title":"Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts","created":"2025-10-15","cited_by_count":4,"area":"safety"},{"id":"2601.03889","title":"Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures","created":"2026-01-07","cited_by_count":4,"area":"moe"},{"id":"2603.18297","title":"Path-Constrained Mixture-of-Experts","created":"2026-03-18","cited_by_count":4,"area":"moe"},{"id":"2605.12476","title":"Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts","created":"2026-05-12","cited_by_count":4,"area":"moe"},{"id":"2403.08477","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","created":"2024-03-13","cited_by_count":3,"area":null},{"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":"2406.15883","title":"SimSMoE: Solving Representational Collapse via Similarity Measure","created":"2024-06-22","cited_by_count":3,"area":"moe"},{"id":"2510.02345","title":"Breaking the MoE LLM Trilemma: Dynamic Expert Clustering with Structured Compression","created":"2025-09-27","cited_by_count":3,"area":"moe"},{"id":"2510.16138","title":"Expert Merging in Sparse Mixture of Experts with Nash Bargaining","created":"2025-10-17","cited_by_count":3,"area":"moe"},{"id":"2510.16448","title":"Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts","created":"2025-10-18","cited_by_count":3,"area":"mllm"},{"id":"2602.01103","title":"Probing RLVR training instability through the lens of objective-level hacking","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2602.12556","title":"SD-MoE: Spectral Decomposition for Effective Expert Specialization","created":"2026-02-13","cited_by_count":3,"area":"moe"},{"id":"2507.21567","title":"RelMap: Enhancing Online Map Construction with Class-Aware Spatial Relation and Semantic Priors","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2510.04331","title":"DoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks","created":"2025-10-05","cited_by_count":2,"area":null},{"id":"2602.17798","title":"Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds","created":"2026-02-19","cited_by_count":2,"area":"moe"},{"id":"2603.12645","title":"LightMoE: Reducing Mixture-of-Experts Redundancy through Expert Replacing","created":"2026-03-13","cited_by_count":2,"area":"moe"},{"id":"2605.20247","title":"CP-MoE: Consistency-Preserving Mixture-of-Experts for Continual Learning","created":"2026-05-18","cited_by_count":2,"area":"moe"},{"id":"2502.12455","title":"DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs","created":"2025-02-18","cited_by_count":1,"area":"moe"},{"id":"2503.22996","title":"Rethinking Sparse Mixture of Experts from a Unified Perspective","created":"2025-03-29","cited_by_count":1,"area":"moe"},{"id":"2503.23924","title":"Model Hemorrhage and the Robustness Limits of Large Language Models","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2505.13380","title":"CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition","created":"2025-05-19","cited_by_count":1,"area":"moe"},{"id":"2509.00679","title":"Router Upcycling: Leveraging Mixture-of-Routers in Mixture-of-Experts Upcycling","created":"2025-08-31","cited_by_count":1,"area":"moe"},{"id":"2509.18912","title":"Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2509.23830","title":"Bayesian Mixture-of-Experts: Towards Making LLMs Know What They Don't Know","created":"2025-09-28","cited_by_count":1,"area":"moe"},{"id":"2602.02685","title":"Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models","created":"2026-02-02","cited_by_count":1,"area":"diffusion"},{"id":"2603.10079","title":"Large Spikes in Stochastic Gradient Descent: A Large-Deviations View","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2605.30992","title":"Eigenvectors of Experts are Training-free Non-collapsing Routers","created":"2026-05-29","cited_by_count":1,"area":"moe"},{"id":"2606.00395","title":"PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement Learning","created":"2026-05-29","cited_by_count":1,"area":"moe"},{"id":"2606.17816","title":"Conservation Laws for Modern Neural Architectures","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2305.03949","title":"Label-Free Multi-Domain Machine Translation with Stage-wise Training","created":"2023-05-06","cited_by_count":0,"area":null},{"id":"2305.14066","title":"One-stop Training of Multiple Capacity Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2603.23495","title":"VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions","created":"2026-03-24","cited_by_count":0,"area":"mllm"},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.08565","title":"Dynamic sparsity in tree-structured feed-forward layers at scale","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.10496","title":"CodeQuant: Unified Clustering and Quantization for Enhanced Outlier Smoothing in Low-Precision Mixture-of-Experts","created":"2026-04-12","cited_by_count":0,"area":"moe"},{"id":"2604.14500","title":"Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection","created":"2026-04-16","cited_by_count":0,"area":"moe"},{"id":"2604.21330","title":"Teacher-Guided Routing for Sparse Vision Mixture-of-Experts","created":"2026-04-23","cited_by_count":0,"area":"moe"},{"id":"2605.17743","title":"MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation","created":"2026-05-18","cited_by_count":0,"area":"distill"},{"id":"2606.10369","title":"PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning","created":"2026-06-09","cited_by_count":0,"area":"moe"},{"id":"2606.14243","title":"Decoupled Mixture-of-Experts for Parametric Knowledge Injection","created":"2026-06-12","cited_by_count":0,"area":"moe"},{"id":"2607.16562","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","created":"2026-07-18","cited_by_count":0,"area":"moe"},{"id":"2608.04084","title":"SpecDrop: Parameter-Free Category-Conditioned Routing for Modular Specialization","created":"2026-08-04","cited_by_count":0,"area":"moe"},{"id":"2608.12419","title":"LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining","created":"2026-08-12","cited_by_count":0,"area":"moe"},{"id":"2608.15787","title":"Routing Divergence Is Not Evidence of Behavioral Influence in Same-Weight MoE Self-Distillation","created":"2026-08-16","cited_by_count":0,"area":"moe"},{"id":"2608.21840","title":"More Experts, Worse Dynamics: Inverse Scaling and Spectral Bias in Mixture-of-Experts State-Space Models","created":"2026-08-22","cited_by_count":0,"area":"moe"},{"id":"2609.31631","title":"OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit","created":"2026-09-09","cited_by_count":0,"area":"moe"},{"id":"2610.02907","title":"Do ResNets Route? Sparse Interaction Experts in Residual Networks","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}