{"total":73,"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":"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":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175,"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":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96,"area":"moe"},{"id":"2402.00433","title":"Merging Multi-Task Models via Weight-Ensembling Mixture of Experts","created":"2024-02-01","cited_by_count":85,"area":"moe"},{"id":"1704.06363","title":"Hard Mixtures of Experts for Large Scale Weakly Supervised Vision","created":"2017-04-20","cited_by_count":67,"area":"moe"},{"id":"2210.03885","title":"Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts","created":"2022-10-08","cited_by_count":50,"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":"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":"2406.12034","title":"Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts","created":"2024-06-17","cited_by_count":23,"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":"2304.01279","title":"Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge Excavation","created":"2023-04-03","cited_by_count":22,"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":"2411.02433","title":"SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Models","created":"2024-11-01","cited_by_count":16,"area":"moe"},{"id":"1906.06717","title":"Mo\\\"ET: Mixture of Expert Trees and its Application to Verifiable Reinforcement Learning","created":"2019-06-16","cited_by_count":12,"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":"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":"2411.02115","title":"FedMoE-DA: Federated Mixture of Experts via Domain Aware Fine-grained Aggregation","created":"2024-11-04","cited_by_count":11,"area":"moe"},{"id":"2107.04694","title":"Lifelong Mixture of Variational Autoencoders","created":"2021-07-09","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":"2510.14436","title":"MergeMoE: Efficient Compression of MoE Models via Expert Output Merging","created":"2025-10-16","cited_by_count":10,"area":"moe"},{"id":"2406.04801","title":"MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks","created":"2024-06-07","cited_by_count":9,"area":"moe"},{"id":"2307.08941","title":"MLP Fusion: Towards Efficient Fine-tuning of Dense and Mixture-of-Experts Language Models","created":"2023-07-18","cited_by_count":6,"area":"moe"},{"id":"2502.12947","title":"Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models","created":"2025-02-18","cited_by_count":6,"area":"moe"},{"id":"2402.16918","title":"m2mKD: Module-to-Module Knowledge Distillation for Modular Transformers","created":"2024-02-26","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":"2312.01361","title":"MoEC: Mixture of Experts Implicit Neural Compression","created":"2023-12-03","cited_by_count":4,"area":"moe"},{"id":"2407.19610","title":"Mixture of Modular Experts: Distilling Knowledge from a Multilingual Teacher into Specialized Modular Language Models","created":"2024-07-28","cited_by_count":4,"area":"moe"},{"id":"2408.04278","title":"LaDiMo: Layer-wise Distillation Inspired MoEfier","created":"2024-08-08","cited_by_count":4,"area":"moe"},{"id":"2507.17133","title":"BrownoutServe: SLO-Aware Inference Serving under Bursty Workloads for MoE-based LLMs","created":"2025-07-23","cited_by_count":4,"area":"moe"},{"id":"2605.18643","title":"Post-Trained MoE Can Skip Half Experts via Self-Distillation","created":"2026-05-18","cited_by_count":4,"area":"moe"},{"id":"2209.08326","title":"Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition","created":"2022-09-17","cited_by_count":3,"area":"moe"},{"id":"2605.27081","title":"ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inference","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2605.28042","title":"Extracting Small Translation Specialists from LLMs by Aggressively Pruning Experts","created":"2026-05-27","cited_by_count":3,"area":"moe"},{"id":"1810.05788","title":"Mixture of Expert/Imitator Networks: Scalable Semi-supervised Learning Framework","created":"2018-10-13","cited_by_count":2,"area":"moe"},{"id":"2405.06059","title":"A Mixture-of-Experts Approach to Few-Shot Task Transfer in Open-Ended Text Worlds","created":"2024-05-09","cited_by_count":2,"area":"moe"},{"id":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2505.19699","title":"Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments","created":"2025-05-26","cited_by_count":2,"area":"moe"},{"id":"2510.16968","title":"Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures","created":"2025-10-19","cited_by_count":2,"area":"moe"},{"id":"2510.19210","title":"MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting","created":"2025-10-22","cited_by_count":2,"area":"moe"},{"id":"2602.01219","title":"Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights","created":"2026-02-01","cited_by_count":2,"area":"moe"},{"id":"2607.24434","title":"DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference","created":"2026-07-27","cited_by_count":2,"area":"moe"},{"id":"2411.13004","title":"MERLOT: A Distilled LLM-based Mixture-of-Experts Framework for Scalable Encrypted Traffic Classification","created":"2024-11-20","cited_by_count":1,"area":"moe"},{"id":"2412.10028","title":"Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts","created":"2024-12-13","cited_by_count":1,"area":"moe"},{"id":"2505.17639","title":"PreMoE: Proactive Inference for Efficient Mixture-of-Experts","created":"2025-05-23","cited_by_count":1,"area":"moe"},{"id":"2511.11505","title":"FarSkip-Collective: Unhobbling Blocking Communication in Mixture of Experts Models","created":"2025-11-14","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":"2605.28207","title":"Pruning and Distilling Mixture-of-Experts into Dense Language Models","created":"2026-05-27","cited_by_count":1,"area":"moe"},{"id":"2607.08250","title":"On the Design of Mixture-of-Experts for Dynamic Gaussian Splatting","created":"2026-07-09","cited_by_count":1,"area":"moe"},{"id":"2608.00916","title":"Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget","created":"2026-08-02","cited_by_count":1,"area":"moe"},{"id":"2201.04042","title":"Towards Lightweight Neural Animation : Exploration of Neural Network Pruning in Mixture of Experts-based Animation Models","created":"2022-01-11","cited_by_count":0,"area":"moe"},{"id":"2209.13071","title":"Diversified Dynamic Routing for Vision Tasks","created":"2022-09-26","cited_by_count":0,"area":"moe"},{"id":"2403.01994","title":"Improving the Downstream Performance of Mixture-of-Experts Transformers via Weak Vanilla Transformers","created":"2024-03-04","cited_by_count":0,"area":"moe"},{"id":"2501.06884","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","created":"2025-01-12","cited_by_count":0,"area":"moe"},{"id":"2506.18349","title":"SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation","created":"2025-06-23","cited_by_count":0,"area":"moe"},{"id":"2508.07144","title":"Dynamic Pattern Alignment Learning for Pretraining Lightweight Human-Centric Vision Models","created":"2025-08-10","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":"2602.19938","title":"A Replicate-and-Quantize Strategy for Plug-and-Play Load Balancing of Sparse Mixture-of-Experts LLMs","created":"2026-02-23","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":"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":"2606.27089","title":"TMP: Tree-structured Mixed-policy Pruning for Large-scale Image Generation and Editing","created":"2026-06-25","cited_by_count":0,"area":"moe"},{"id":"2608.10823","title":"MoE Proxy Models for Low-Cost Failure Reproduction and Diagnosis in LLM RL Post-Training","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2608.23806","title":"Giga-Embeddings: Mixture-of-Experts Encoders for High-Throughput Text Embeddings","created":"2026-08-24","cited_by_count":0,"area":"moe"},{"id":"2608.25371","title":"Capacity Overflow: A Blind Spot for Backdoor Attacks in Vision MoE","created":"2026-08-26","cited_by_count":0,"area":"moe"},{"id":"2609.06076","title":"Beyond Retraining-Free MoE Compression: A Cost-Normalized Study of Post-Compression Adjustment","created":"2026-09-05","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":"2609.21137","title":"A Multi-Engine Dataflow for MoE Decoding on Scratchpad-Based Tensor Accelerators","created":"2026-09-17","cited_by_count":0,"area":"moe"},{"id":"2609.21672","title":"Accelerating Dense LLMs via L0-regularized Mixture-of-Experts","created":"2026-09-18","cited_by_count":0,"area":"moe"},{"id":"2610.05458","title":"Measuring and Reducing Cross-Vendor Mismatch in Language Models","created":"2026-10-04","cited_by_count":0,"area":"moe"},{"id":"2610.20238","title":"MAEM: Mitigating Recency Bias via a Replay-Free, Capacity-Controlled Dynamic Mixture of Experts for Class-Incremental Graph Learning","created":"2026-10-14","cited_by_count":0,"area":"moe"}],"next_cursor":null}