{"list":"other","total":106,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1511.06434","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","created":"2015-11-19","cited_by_count":2054},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"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":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"2207.04672","title":"No Language Left Behind: Scaling Human-Centered Machine Translation","created":"2022-07-11","cited_by_count":1312},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2412.19437","title":"DeepSeek-V3 Technical Report","created":"2024-12-27","cited_by_count":811},{"id":"1712.01312","title":"Learning Sparse Neural Networks through $L_0$ Regularization","created":"2017-12-04","cited_by_count":583},{"id":"1603.01360","title":"Neural Architectures for Named Entity Recognition","created":"2016-03-04","cited_by_count":550},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"1803.00676","title":"Meta-Learning for Semi-Supervised Few-Shot Classification","created":"2018-03-02","cited_by_count":456},{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401},{"id":"2202.08906","title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","created":"2022-02-17","cited_by_count":399},{"id":"1509.00685","title":"A Neural Attention Model for Abstractive Sentence Summarization","created":"2015-09-02","cited_by_count":396},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"2409.16040","title":"Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts","created":"2024-09-24","cited_by_count":287},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"2401.16386","title":"Continual Learning with Pre-Trained Models: A Survey","created":"2024-01-29","cited_by_count":154},{"id":"1508.01745","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","created":"2015-08-07","cited_by_count":134},{"id":"2001.00689","title":"A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning","created":"2020-01-03","cited_by_count":134},{"id":"1902.11175","title":"One-Shot Federated Learning","created":"2019-02-28","cited_by_count":125},{"id":"2407.04051","title":"FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs","created":"2024-07-04","cited_by_count":122},{"id":"2405.11273","title":"Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts","created":"2024-05-18","cited_by_count":108},{"id":"2102.04925","title":"FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation","created":"2021-02-09","cited_by_count":98},{"id":"2110.03742","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","created":"2021-09-24","cited_by_count":96},{"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},{"id":"2206.04046","title":"Sparse Mixture-of-Experts are Domain Generalizable Learners","created":"2022-06-08","cited_by_count":85},{"id":"2401.16160","title":"LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMs","created":"2024-01-29","cited_by_count":84},{"id":"2202.02931","title":"TRGP: Trust Region Gradient Projection for Continual Learning","created":"2022-02-07","cited_by_count":82},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78},{"id":"2403.07652","title":"Harder Tasks Need More Experts: Dynamic Routing in MoE Models","created":"2024-03-12","cited_by_count":72},{"id":"1809.02256","title":"Multi-Source Domain Adaptation with Mixture of Experts","created":"2018-09-07","cited_by_count":62},{"id":"2406.16437","title":"Theory on Mixture-of-Experts in Continual Learning","created":"2024-06-24","cited_by_count":54},{"id":"2208.02813","title":"Towards Understanding Mixture of Experts in Deep Learning","created":"2022-08-04","cited_by_count":52},{"id":"2204.07689","title":"Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners","created":"2022-04-16","cited_by_count":51},{"id":"2408.12570","title":"Jamba-1.5: Hybrid Transformer-Mamba Models at Scale","created":"2024-08-22","cited_by_count":50},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49},{"id":"2412.12953","title":"Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning","created":"2024-12-17","cited_by_count":48},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47},{"id":"2401.09561","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","created":"2024-01-17","cited_by_count":44},{"id":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44},{"id":"2310.16795","title":"QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models","created":"2023-10-25","cited_by_count":42},{"id":"2204.09636","title":"Residual Mixture of Experts","created":"2022-04-20","cited_by_count":39},{"id":"2401.10191","title":"Divide and not forget: Ensemble of selectively trained experts in Continual Learning","created":"2024-01-18","cited_by_count":38},{"id":"2303.06182","title":"Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference","created":"2023-03-10","cited_by_count":37},{"id":"1912.06733","title":"Private Federated Learning with Domain Adaptation","created":"2019-12-13","cited_by_count":36},{"id":"2312.07987","title":"SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention","created":"2023-12-13","cited_by_count":34},{"id":"2402.18377","title":"Out-of-Domain Generalization in Dynamical Systems Reconstruction","created":"2024-02-28","cited_by_count":33},{"id":"2408.10681","title":"HMoE: Heterogeneous Mixture of Experts for Language Modeling","created":"2024-08-20","cited_by_count":29},{"id":"2107.06724","title":"Federated Mixture of Experts","created":"2021-07-14","cited_by_count":28},{"id":"2104.09122","title":"Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning","created":"2021-04-19","cited_by_count":27},{"id":"2411.15708","title":"LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training","created":"2024-11-24","cited_by_count":26},{"id":"2301.06387","title":"PECAN: Leveraging Policy Ensemble for Context-Aware Zero-Shot Human-AI Coordination","created":"2023-01-16","cited_by_count":25},{"id":"2412.06647","title":"Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset","created":"2024-12-09","cited_by_count":25},{"id":"2010.02056","title":"Specialized federated learning using a mixture of experts","created":"2020-10-05","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":"2410.14972","title":"MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning","created":"2024-10-19","cited_by_count":23},{"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},{"id":"1702.06856","title":"Robustness to Adversarial Examples through an Ensemble of Specialists","created":"2017-02-22","cited_by_count":21},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21},{"id":"2205.09284","title":"Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemble","created":"2022-05-19","cited_by_count":18},{"id":"2405.17976","title":"Yuan 2.0-M32: Mixture of Experts with Attention Router","created":"2024-05-28","cited_by_count":18},{"id":"2309.14976","title":"MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection","created":"2023-09-26","cited_by_count":17},{"id":"2405.14131","title":"Statistical Advantages of Perturbing Cosine Router in Mixture of Experts","created":"2024-05-23","cited_by_count":16},{"id":"2408.11396","title":"MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing","created":"2024-08-21","cited_by_count":16},{"id":"1805.02481","title":"MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation","created":"2018-05-07","cited_by_count":15},{"id":"2412.04220","title":"Customize Segment Anything Model for Multi-Modal Semantic Segmentation with Mixture of LoRA Experts","created":"2024-12-05","cited_by_count":15},{"id":"2403.06966","title":"Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts","created":"2024-03-11","cited_by_count":14},{"id":"2405.11530","title":"Learning More Generalized Experts by Merging Experts in Mixture-of-Experts","created":"2024-05-19","cited_by_count":12},{"id":"2411.18322","title":"Mixture of Experts in Image Classification: What's the Sweet Spot?","created":"2024-11-27","cited_by_count":11},{"id":"2407.09816","title":"MaskMoE: Boosting Token-Level Learning via Routing Mask in Mixture-of-Experts","created":"2024-07-13","cited_by_count":9},{"id":"2110.12667","title":"Mixture-of-Variational-Experts for Continual Learning","created":"2021-10-25","cited_by_count":8},{"id":"2407.21571","title":"PMoE: Progressive Mixture of Experts with Asymmetric Transformer for Continual Learning","created":"2024-07-31","cited_by_count":8},{"id":"2306.08586","title":"Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings","created":"2023-06-14","cited_by_count":7},{"id":"2403.11311","title":"Mixture-of-Prompt-Experts for Multi-modal Semantic Understanding","created":"2024-03-17","cited_by_count":7},{"id":"2210.08121","title":"Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptors","created":"2022-10-17","cited_by_count":6},{"id":"2406.03140","title":"Continual Traffic Forecasting via Mixture of Experts","created":"2024-06-05","cited_by_count":6},{"id":"2412.09952","title":"Llama 3 Meets MoE: Efficient Upcycling","created":"2024-12-13","cited_by_count":6},{"id":"2412.11608","title":"Towards Adversarial Robustness of Model-Level Mixture-of-Experts Architectures for Semantic Segmentation","created":"2024-12-16","cited_by_count":5},{"id":"2412.15690","title":"Theory of Mixture-of-Experts for Mobile Edge Computing","created":"2024-12-20","cited_by_count":5},{"id":"2206.07832","title":"Adaptive Expert Models for Personalization in Federated Learning","created":"2022-06-15","cited_by_count":4},{"id":"2108.09618","title":"Personalised Federated Learning: A Combinational Approach","created":"2021-08-22","cited_by_count":3}],"next_cursor":"100"}