{"total":98,"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":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623,"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":"2110.01786","title":"MoEfication: Transformer Feed-forward Layers are Mixtures of Experts","created":"2021-10-05","cited_by_count":152,"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":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108,"area":"moe"},{"id":"2402.08562","title":"Higher Layers Need More LoRA Experts","created":"2024-02-13","cited_by_count":102,"area":"moe"},{"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":"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":"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":"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":"2204.07689","title":"Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners","created":"2022-04-16","cited_by_count":51,"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":"2406.13233","title":"AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models","created":"2024-06-19","cited_by_count":44,"area":"moe"},{"id":"2505.22323","title":"Advancing Expert Specialization for Better MoE","created":"2025-05-28","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":"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":"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":"2405.03133","title":"Lory: Fully Differentiable Mixture-of-Experts for Autoregressive Language Model Pre-training","created":"2024-05-06","cited_by_count":37,"area":"moe"},{"id":"2502.07972","title":"Training Sparse Mixture Of Experts Text Embedding Models","created":"2025-02-11","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":"2409.06211","title":"STUN: Structured-Then-Unstructured Pruning for Scalable MoE Pruning","created":"2024-09-10","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":"2402.12656","title":"HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts","created":"2024-02-20","cited_by_count":26,"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":"2406.02500","title":"Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques","created":"2024-06-04","cited_by_count":24,"area":"moe"},{"id":"2410.21804","title":"Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging","created":"2024-10-29","cited_by_count":23,"area":"moe"},{"id":"2502.16894","title":"Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment","created":"2025-02-24","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":"2410.10054","title":"AlphaLoRA: Assigning LoRA Experts Based on Layer Training Quality","created":"2024-10-14","cited_by_count":20,"area":"moe"},{"id":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18,"area":"moe"},{"id":"2310.00811","title":"Sparse Backpropagation for MoE Training","created":"2023-10-01","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":"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":"2503.05066","title":"Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts","created":"2025-03-07","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":"2509.25684","title":"LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts","created":"2025-09-30","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":"2504.00661","title":"DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism","created":"2025-04-01","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":"2407.11030","title":"DLO: Dynamic Layer Operation for Efficient Vertical Scaling of LLMs","created":"2024-07-03","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":"2503.23100","title":"MoLAE: Mixture of Latent Experts for Parameter-Efficient Language Models","created":"2025-03-29","cited_by_count":10,"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":"2502.15828","title":"A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models","created":"2025-02-20","cited_by_count":9,"area":"moe"},{"id":"2406.12375","title":"GW-MoE: Resolving Uncertainty in MoE Router with Global Workspace Theory","created":"2024-06-18","cited_by_count":8,"area":"moe"},{"id":"2306.04845","title":"Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts","created":"2023-06-08","cited_by_count":7,"area":"moe"},{"id":"2402.15082","title":"PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning","created":"2024-02-23","cited_by_count":7,"area":"moe"},{"id":"2404.02356","title":"Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors","created":"2024-04-02","cited_by_count":7,"area":"moe"},{"id":"2501.13074","title":"Autonomy-of-Experts Models","created":"2025-01-22","cited_by_count":7,"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":"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":"2509.02753","title":"LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference","created":"2025-09-02","cited_by_count":6,"area":"moe"},{"id":"2503.11144","title":"MoLEx: Mixture of Layer Experts for Finetuning with Sparse Upcycling","created":"2025-03-14","cited_by_count":5,"area":"moe"},{"id":"2506.14436","title":"MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation","created":"2025-06-17","cited_by_count":5,"area":"moe"},{"id":"2506.21035","title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","created":"2025-06-26","cited_by_count":5,"area":"moe"},{"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":"2505.13345","title":"Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference","created":"2025-05-19","cited_by_count":4,"area":"moe"},{"id":"2512.19765","title":"How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts","created":"2025-12-21","cited_by_count":4,"area":"moe"},{"id":"2604.08133","title":"Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference","created":"2026-04-09","cited_by_count":4,"area":"moe"},{"id":"2305.02176","title":"Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity","created":"2023-05-03","cited_by_count":3,"area":"moe"},{"id":"2504.12359","title":"Unveiling Hidden Collaboration within Mixture-of-Experts in Large Language Models","created":"2025-04-16","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":"2510.16411","title":"Modeling Expert Interactions in Sparse Mixture of Experts via Graph Structures","created":"2025-10-18","cited_by_count":3,"area":"moe"},{"id":"2604.19048","title":"SAMoRA: Semantic-Aware Mixture of LoRA Experts for Task-Adaptive Learning","created":"2026-04-21","cited_by_count":3,"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":"2502.03884","title":"Rank Also Matters: Hierarchical Configuration for Mixture of Adapter Experts in LLM Fine-Tuning","created":"2025-02-06","cited_by_count":2,"area":"moe"},{"id":"2601.06356","title":"Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning","created":"2026-01-09","cited_by_count":2,"area":"moe"},{"id":"2601.06790","title":"SecMoE: Communication-Efficient Secure MoE Inference via Select-Then-Compute","created":"2026-01-11","cited_by_count":2,"area":"moe"},{"id":"2403.02436","title":"How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers","created":"2024-03-04","cited_by_count":1,"area":"moe"},{"id":"2508.18376","title":"DualSparse-MoE: Coordinating Tensor/Neuron-Level Sparsity with Expert Partition and Reconstruction","created":"2025-08-25","cited_by_count":1,"area":"moe"},{"id":"2511.19480","title":"Exploiting the Experts: Unauthorized Compression in MoE-LLMs","created":"2025-11-22","cited_by_count":1,"area":"moe"},{"id":"2604.06291","title":"TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models","created":"2026-04-07","cited_by_count":1,"area":"moe"},{"id":"2605.25565","title":"RotMoLE: Enhancing Mixture of Low-Rank Experts through Rotational Gating Mechanism","created":"2026-05-25","cited_by_count":1,"area":"moe"},{"id":"2509.10530","title":"Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts","created":"2025-09-05","cited_by_count":0,"area":"moe"},{"id":"2509.19781","title":"Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference","created":"2025-09-24","cited_by_count":0,"area":"moe"},{"id":"2603.12577","title":"Expert Pyramid Tuning: Efficient Parameter Fine-Tuning for Expertise-Driven Task Allocation","created":"2026-03-13","cited_by_count":0,"area":"moe"},{"id":"2603.27965","title":"ExFusion: Efficient Transformer Training via Multi-Experts Fusion","created":"2026-03-30","cited_by_count":0,"area":"moe"},{"id":"2604.01762","title":"FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models","created":"2026-04-02","cited_by_count":0,"area":"moe"},{"id":"2604.02338","title":"LiME: Lightweight Mixture of Experts for Efficient Multimodal Multi-task Learning","created":"2026-02-01","cited_by_count":0,"area":"moe"},{"id":"2605.04058","title":"MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning","created":"2026-04-10","cited_by_count":0,"area":"moe"},{"id":"2606.08814","title":"STAR: Rethinking MoE Routing as Structure-Aware Subspace Learning","created":"2026-06-07","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":"2608.10392","title":"Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2608.21878","title":"ViSMoE: Visual-Aware Sparse Mixture-of-Experts for Embodied Referring Expression Grounding","created":"2026-08-22","cited_by_count":0,"area":"moe"},{"id":"2609.05770","title":"RAPTOR: Role-Aware Private Training for Mixture-of-Experts","created":"2026-09-04","cited_by_count":0,"area":"moe"},{"id":"2609.33614","title":"EAT: Expert Account Tracker for Efficient MoE Inference","created":"2026-09-27","cited_by_count":0,"area":"moe"},{"id":"2610.01418","title":"SpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-Experts","created":"2026-10-01","cited_by_count":0,"area":"moe"},{"id":"2610.19033","title":"How Many Ranks Does a Token Need? A Noise-Floor Squelch for Rank-One LoRA Experts","created":"2026-10-13","cited_by_count":0,"area":"moe"}],"next_cursor":null}