{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2508.10925","title":"gpt-oss-120b & gpt-oss-20b Model Card","created":"2025-08-08","cited_by_count":1386},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2104.04473","title":"Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM","created":"2021-04-09","cited_by_count":632},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"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},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300},{"id":"1802.05799","title":"Horovod: fast and easy distributed deep learning in TensorFlow","created":"2018-02-15","cited_by_count":279},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"2211.15841","title":"MegaBlocks: Efficient Sparse Training with Mixture-of-Experts","created":"2022-11-29","cited_by_count":209},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"2206.03382","title":"Tutel: Adaptive Mixture-of-Experts at Scale","created":"2022-06-07","cited_by_count":201},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187},{"id":"2311.08105","title":"DiLoCo: Distributed Low-Communication Training of Language Models","created":"2023-11-14","cited_by_count":121},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108},{"id":"2110.14883","title":"Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training","created":"2021-10-28","cited_by_count":96},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91},{"id":"2209.01188","title":"Petals: Collaborative Inference and Fine-tuning of Large Models","created":"2022-09-02","cited_by_count":87},{"id":"2505.16278","title":"DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Driving","created":"2025-05-22","cited_by_count":86},{"id":"2109.10465","title":"Scalable and Efficient MoE Training for Multitask Multilingual Models","created":"2021-09-22","cited_by_count":76},{"id":"2504.19580","title":"ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving","created":"2025-04-28","cited_by_count":67},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59},{"id":"2406.06563","title":"Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models","created":"2024-06-03","cited_by_count":59},{"id":"2106.10207","title":"Distributed Deep Learning in Open Collaborations","created":"2021-06-18","cited_by_count":58},{"id":"2501.11873","title":"Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models","created":"2025-01-21","cited_by_count":54},{"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},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47},{"id":"2404.10237","title":"Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models","created":"2024-04-16","cited_by_count":46},{"id":"2002.04013","title":"Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Experts","created":"2020-02-10","cited_by_count":43},{"id":"2203.14685","title":"HetuMoE: An Efficient Trillion-scale Mixture-of-Expert Distributed Training System","created":"2022-03-28","cited_by_count":36},{"id":"2211.02131","title":"Safe Real-World Autonomous Driving by Learning to Predict and Plan with a Mixture of Experts","created":"2022-11-03","cited_by_count":29},{"id":"2408.10681","title":"HMoE: Heterogeneous Mixture of Experts for Language Modeling","created":"2024-08-20","cited_by_count":29},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26},{"id":"2405.09446","title":"M$^4$oE: A Foundation Model for Medical Multimodal Image Segmentation with Mixture of Experts","created":"2024-05-15","cited_by_count":26},{"id":"2407.07852","title":"OpenDiLoCo: An Open-Source Framework for Globally Distributed Low-Communication Training","created":"2024-07-10","cited_by_count":24},{"id":"2105.14450","title":"Maximizing Parallelism in Distributed Training for Huge Neural Networks","created":"2021-05-30","cited_by_count":23},{"id":"2409.19291","title":"CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling","created":"2024-09-28","cited_by_count":23},{"id":"2410.15774","title":"Generalizing Motion Planners with Mixture of Experts for Autonomous Driving","created":"2024-10-21","cited_by_count":22},{"id":"2502.18535","title":"A Survey of Zero-Knowledge Proof Based Verifiable Machine Learning","created":"2025-02-25","cited_by_count":22},{"id":"1911.04610","title":"XPipe: Efficient Pipeline Model Parallelism for Multi-GPU DNN Training","created":"2019-10-24","cited_by_count":20},{"id":"2309.01172","title":"FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs","created":"2023-09-03","cited_by_count":20},{"id":"2310.14848","title":"Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey","created":"2023-10-23","cited_by_count":18},{"id":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18},{"id":"2505.21411","title":"Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity","created":"2025-05-27","cited_by_count":18},{"id":"2006.05911","title":"Continuous Action Reinforcement Learning from a Mixture of Interpretable Experts","created":"2020-06-10","cited_by_count":17},{"id":"2406.13583","title":"Low-Rank Mixture-of-Experts for Continual Medical Image Segmentation","created":"2024-06-19","cited_by_count":16},{"id":"2501.05450","title":"Decentralized Diffusion Models","created":"2025-01-09","cited_by_count":13},{"id":"2505.04519","title":"Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs","created":"2025-05-07","cited_by_count":12},{"id":"2506.08356","title":"MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding","created":"2025-06-10","cited_by_count":10},{"id":"2410.21086","title":"Efficient Mixture-of-Expert for Video-based Driver State and Physiological Multi-task Estimation in Conditional Autonomous Driving","created":"2024-10-28","cited_by_count":9},{"id":"2503.10412","title":"dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis","created":"2025-03-13","cited_by_count":9},{"id":"2501.07288","title":"LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networks","created":"2025-01-13","cited_by_count":7},{"id":"2504.03871","title":"HeterMoE: Efficient Training of Mixture-of-Experts Models on Heterogeneous GPUs","created":"2025-04-04","cited_by_count":7},{"id":"2410.07192","title":"PipeFill: Using GPUs During Bubbles in Pipeline-parallel LLM Training","created":"2024-09-23","cited_by_count":5},{"id":"2009.08876","title":"Multi-modal Experts Network for Autonomous Driving","created":"2020-09-18","cited_by_count":4},{"id":"2312.00839","title":"PipeOptim: Ensuring Effective 1F1B Schedule with Optimizer-Dependent Weight Prediction","created":"2023-12-01","cited_by_count":4},{"id":"2410.07234","title":"A Dynamic Approach to Stock Price Prediction: Comparing RNN and Mixture of Experts Models Across Different Volatility Profiles","created":"2024-10-04","cited_by_count":4},{"id":"2506.21263","title":"DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster","created":"2025-06-26","cited_by_count":4},{"id":"2403.01008","title":"BasedAI: A decentralized P2P network for Zero Knowledge Large Language Models (ZK-LLMs)","created":"2024-03-01","cited_by_count":3},{"id":"2505.08944","title":"Toward Cost-Efficient Serving of Mixture-of-Experts with Asynchrony","created":"2025-05-13","cited_by_count":3},{"id":"2401.01728","title":"Ravnest: Decentralized Asynchronous Training on Heterogeneous Devices","created":"2024-01-03","cited_by_count":2},{"id":"2403.10504","title":"ATOM: Asynchronous Training of Massive Models for Deep Learning in a Decentralized Environment","created":"2024-03-15","cited_by_count":2},{"id":"2503.05800","title":"How Do Consumers Really Choose: Exposing Hidden Preferences with the Mixture of Experts Model","created":"2025-03-03","cited_by_count":2},{"id":"2504.12234","title":"MOS: Towards Effective Smart Contract Vulnerability Detection through Mixture-of-Experts Tuning of Large Language Models","created":"2025-04-16","cited_by_count":2},{"id":"2507.22371","title":"SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection","created":"2025-07-30","cited_by_count":2},{"id":"2207.07578","title":"Quantitative Stock Investment by Routing Uncertainty-Aware Trading Experts: A Multi-Task Learning Approach","created":"2022-06-07","cited_by_count":1},{"id":"2407.19401","title":"Towards Secure and Private AI: A Framework for Decentralized Inference","created":"2024-07-28","cited_by_count":1},{"id":"2410.21338","title":"FinTeamExperts: Role Specialized MOEs For Financial Analysis","created":"2024-10-28","cited_by_count":1}],"next_cursor":null}