{"total":110,"rows":[{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"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":"2502.16982","title":"Muon is Scalable for LLM Training","created":"2025-02-24","cited_by_count":428,"area":"moe"},{"id":"2409.02060","title":"OLMoE: Open Mixture-of-Experts Language Models","created":"2024-09-03","cited_by_count":301,"area":"moe"},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248,"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":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187,"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":"2404.15159","title":"MixLoRA: Enhancing Large Language Models Fine-Tuning with LoRA-based Mixture of Experts","created":"2024-04-22","cited_by_count":147,"area":"moe"},{"id":"2305.13230","title":"To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis","created":"2023-05-22","cited_by_count":92,"area":"moe"},{"id":"2411.02265","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","created":"2024-11-04","cited_by_count":90,"area":"moe"},{"id":"2309.14393","title":"LLMCarbon: Modeling the end-to-end Carbon Footprint of Large Language Models","created":"2023-09-25","cited_by_count":72,"area":"moe"},{"id":"2407.04153","title":"Mixture of A Million Experts","created":"2024-07-04","cited_by_count":72,"area":"moe"},{"id":"2304.02806","title":"Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling","created":"2023-04-06","cited_by_count":64,"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":"2303.06318","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":"2507.17702","title":"Towards Greater Leverage: Scaling Laws for Efficient Mixture-of-Experts Language Models","created":"2025-07-23","cited_by_count":45,"area":"moe"},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37,"area":"moe"},{"id":"2407.19985","title":"Mixture of Nested Experts: Adaptive Processing of Visual Tokens","created":"2024-07-29","cited_by_count":25,"area":"moe"},{"id":"2308.09723","title":"FineQuant: Unlocking Efficiency with Fine-Grained Weight-Only Quantization for LLMs","created":"2023-08-16","cited_by_count":22,"area":"moe"},{"id":"2503.05139","title":"Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs","created":"2025-03-07","cited_by_count":22,"area":"moe"},{"id":"2510.27234","title":"MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts","created":"2025-10-31","cited_by_count":21,"area":"moe"},{"id":"2404.02852","title":"Toward Inference-optimal Mixture-of-Expert Large Language Models","created":"2024-04-03","cited_by_count":19,"area":"moe"},{"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":"2609.01343","title":"SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers","created":"2026-09-01","cited_by_count":18,"area":"moe"},{"id":"2405.14260","title":"Graph Sparsification via Mixture of Graphs","created":"2024-05-23","cited_by_count":17,"area":"moe"},{"id":"2410.02117","title":"Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices","created":"2024-10-03","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":"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":"2411.06681","title":"WDMoE: Wireless Distributed Mixture of Experts for Large Language Models","created":"2024-11-11","cited_by_count":12,"area":"moe"},{"id":"2508.12461","title":"Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Models","created":"2025-08-17","cited_by_count":11,"area":"moe"},{"id":"2605.09165","title":"Sparse Layers are Critical to Scaling Looped Language Models","created":"2026-05-09","cited_by_count":11,"area":"moe"},{"id":"2509.23678","title":"Towards a Comprehensive Scaling Law of Mixture-of-Experts","created":"2025-09-28","cited_by_count":10,"area":"moe"},{"id":"2305.13999","title":"Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model","created":"2023-05-23","cited_by_count":9,"area":"moe"},{"id":"2508.05257","title":"MoBE: Mixture-of-Basis-Experts for Compressing MoE-based LLMs","created":"2025-08-07","cited_by_count":9,"area":"moe"},{"id":"2506.12119","title":"Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource","created":"2025-06-13","cited_by_count":8,"area":"moe"},{"id":"2603.04971","title":"Mixture of Universal Experts: Scaling Virtual Width via Depth-Width Transformation","created":"2026-03-05","cited_by_count":8,"area":"moe"},{"id":"2607.16051","title":"Loop the Loopies!","created":"2026-07-17","cited_by_count":8,"area":"moe"},{"id":"2602.09316","title":"Effective MoE-based LLM Compression by Exploiting Heterogeneous Inter-Group Experts Routing Frequency and Information Density","created":"2026-02-10","cited_by_count":7,"area":"moe"},{"id":"2410.16077","title":"CartesianMoE: Boosting Knowledge Sharing among Experts via Cartesian Product Routing in Mixture-of-Experts","created":"2024-10-21","cited_by_count":5,"area":"moe"},{"id":"2503.05029","title":"Continual Pre-training of MoEs: How robust is your router?","created":"2025-03-06","cited_by_count":5,"area":"moe"},{"id":"2601.22101","title":"ECO: Quantized Training without Full-Precision Master Weights","created":"2026-01-29","cited_by_count":5,"area":"moe"},{"id":"2602.01203","title":"Attention Sink Forges Native MoE in Attention Layers: Sink-Aware Training to Address Head Collapse","created":"2026-02-01","cited_by_count":5,"area":"moe"},{"id":"2605.20948","title":"Memory Grafting: Scaling Language Model Pre-training via Offline Conditional Memory","created":"2026-05-20","cited_by_count":5,"area":"moe"},{"id":"2304.11414","title":"Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism","created":"2023-04-22","cited_by_count":4,"area":"moe"},{"id":"2506.21328","title":"Latent Prototype Routing: Achieving Near-Perfect Load Balancing in Mixture-of-Experts","created":"2025-06-26","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":"2603.18297","title":"Path-Constrained Mixture-of-Experts","created":"2026-03-18","cited_by_count":4,"area":"moe"},{"id":"2604.10152","title":"SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding","created":"2026-04-11","cited_by_count":4,"area":"moe"},{"id":"2605.24956","title":"NITP: Next Implicit Token Prediction for LLM Pre-training","created":"2026-05-24","cited_by_count":4,"area":"moe"},{"id":"2606.17952","title":"SoftMoE: Soft Differentiable Routing for Mixture-of-Experts in LLMs","created":"2026-06-16","cited_by_count":4,"area":"moe"},{"id":"2607.14530","title":"xHC: Expanded Hyper-Connections","created":"2026-07-16","cited_by_count":4,"area":"moe"},{"id":"2412.15411","title":"Sparse Checkpointing for Fast and Reliable MoE Training","created":"2024-12-19","cited_by_count":3,"area":"moe"},{"id":"2507.09955","title":"DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models","created":"2025-07-14","cited_by_count":3,"area":"moe"},{"id":"2509.24406","title":"Muon: Training and Trade-offs with Latent Attention and MoE","created":"2025-09-29","cited_by_count":3,"area":"moe"},{"id":"2601.03577","title":"Variational Inference, Entropy, and Orthogonality: A Unified Theory of Mixture-of-Experts","created":"2026-01-07","cited_by_count":3,"area":"moe"},{"id":"2602.00800","title":"JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation","created":"2026-01-31","cited_by_count":3,"area":"moe"},{"id":"2604.00421","title":"Self-Routing: Parameter-Free Expert Routing from Hidden States","created":"2026-04-01","cited_by_count":3,"area":"moe"},{"id":"2605.27358","title":"MobileMoE: Scaling On-Device Mixture of Experts","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2606.25971","title":"Improving Neural Network Training by Decoupling the Magnitude and Direction of Weight Vectors","created":"2026-06-24","cited_by_count":3,"area":"moe"},{"id":"2504.04342","title":"Pruning Laws for Large Language Models","created":"2025-04-06","cited_by_count":2,"area":"moe"},{"id":"2506.02890","title":"Scaling Fine-Grained MoE Beyond 50B Parameters: Empirical Evaluation and Practical Insights","created":"2025-06-03","cited_by_count":2,"area":"moe"},{"id":"2507.03526","title":"Decoupled Relative Learning Rate Schedules","created":"2025-07-04","cited_by_count":2,"area":"moe"},{"id":"2508.16700","title":"GPT-OSS-20B: A Comprehensive Deployment-Centric Analysis of OpenAI's Open-Weight Mixture of Experts Model","created":"2025-08-22","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":"2601.05296","title":"MoEBlaze: Breaking the Memory Wall for Efficient MoE Training on Modern GPUs","created":"2026-01-08","cited_by_count":2,"area":"moe"},{"id":"2603.21862","title":"Holistic Scaling Laws for Optimal Mixture-of-Experts Architecture Optimization","created":"2026-03-23","cited_by_count":2,"area":"moe"},{"id":"2605.11689","title":"Slicing and Dicing: Configuring Optimal Mixtures of Experts","created":"2026-05-12","cited_by_count":2,"area":"moe"},{"id":"2401.15713","title":"Contrastive Learning and Mixture of Experts Enables Precise Vector Embeddings","created":"2024-01-28","cited_by_count":1,"area":"moe"},{"id":"2506.02965","title":"PC-MoE: Memory-Efficient and Privacy-Preserving Collaborative Training for Mixture-of-Experts LLMs","created":"2025-06-03","cited_by_count":1,"area":"moe"},{"id":"2510.08008","title":"Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts","created":"2025-10-09","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":"2512.03915","title":"A Theoretical Framework for Auxiliary-Loss-Free Load Balancing of Sparse Mixture-of-Experts in Large-Scale AI Models","created":"2025-12-03","cited_by_count":1,"area":"moe"},{"id":"2603.07977","title":"Mixture of experts architectures for machine learning interatomic potentials","created":"2026-03-09","cited_by_count":1,"area":"moe"},{"id":"2603.29765","title":"Training-Free Dynamic Upcycling of Expert Language Models","created":"2026-03-31","cited_by_count":1,"area":"moe"},{"id":"2604.03044","title":"JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency","created":"2026-04-03","cited_by_count":1,"area":"moe"},{"id":"2604.14419","title":"Equifinality in Mixture of Experts: Routing Topology Does Not Determine Language Modeling Quality","created":"2026-04-15","cited_by_count":1,"area":"moe"},{"id":"2605.13769","title":"Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching","created":"2026-05-13","cited_by_count":1,"area":"moe"},{"id":"2606.19036","title":"Geometric and Stochastic Analysis of Discontinuities in Sparse Mixture-of-Experts","created":"2026-06-17","cited_by_count":1,"area":"moe"},{"id":"2609.01244","title":"Post-Training Science for Supervised Fine-Tuning","created":"2026-09-01","cited_by_count":1,"area":"moe"},{"id":"2609.40316","title":"Scaling Laws for Looped Mixture of Experts","created":"2026-09-30","cited_by_count":1,"area":"moe"},{"id":"2410.04511","title":"Realizing Video Summarization from the Path of Language-based Semantic Understanding","created":"2024-10-06","cited_by_count":0,"area":"moe"},{"id":"2508.06617","title":"Generalizing Scaling Laws for Dense and Sparse Large Language Models","created":"2025-08-08","cited_by_count":0,"area":"moe"},{"id":"2601.09200","title":"A.X K1 Technical Report","created":"2026-01-14","cited_by_count":0,"area":"moe"},{"id":"2603.00031","title":"GRIP: Geometric Refinement and Adaptive Information Potential for Data Efficiency","created":"2026-02-04","cited_by_count":0,"area":"moe"},{"id":"2604.09175","title":"Generalization and Scaling Laws for Mixture-of-Experts Transformers","created":"2026-04-10","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":"2605.07731","title":"Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs","created":"2026-05-08","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":"2605.18848","title":"Exact Linear Attention","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2606.19025","title":"FoMoE: Breaking the Full-Replica Barrier with a Federation of MoEs","created":"2026-06-17","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":"2608.07964","title":"EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2608.10605","title":"Compute-Optimal Is Not Cluster-Optimal: Systems-Aware Scaling for Sparse Mixture-of-Experts","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2608.20061","title":"Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts","created":"2026-08-20","cited_by_count":0,"area":"moe"},{"id":"2608.30567","title":"TuringLLM: Efficiently Scaling Foundation Models Toward Physical AI","created":"2026-08-31","cited_by_count":0,"area":"moe"},{"id":"2608.31118","title":"When Does Bigger Help? A Controlled Study of LLM Scale for Ontology Learning","created":"2026-08-31","cited_by_count":0,"area":"moe"},{"id":"2609.02204","title":"TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval","created":"2026-09-02","cited_by_count":0,"area":"moe"},{"id":"2609.08690","title":"Hyperparameter Scaling Laws Across MoE Sparsity","created":"2026-09-08","cited_by_count":0,"area":"moe"}],"next_cursor":"100"}