{"list":"other","total":74,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"2202.09368","title":"Mixture-of-Experts with Expert Choice Routing","created":"2022-02-18","cited_by_count":623},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"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":"2004.02806","title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","created":"2020-04-01","cited_by_count":397},{"id":"2406.12845","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","created":"2024-06-18","cited_by_count":376},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313},{"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":"2311.13165","title":"Multimodal Large Language Models: A Survey","created":"2023-11-22","cited_by_count":195},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2402.14800","title":"Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models","created":"2024-02-22","cited_by_count":146},{"id":"2305.18295","title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","created":"2023-05-29","cited_by_count":142},{"id":"2312.03718","title":"Large Language Models in Law: A Survey","created":"2023-11-26","cited_by_count":128},{"id":"2310.18339","title":"When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications","created":"2023-10-21","cited_by_count":111},{"id":"2308.12066","title":"Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference","created":"2023-08-23","cited_by_count":104},{"id":"2210.14793","title":"M$^3$ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design","created":"2022-10-26","cited_by_count":98},{"id":"2402.03226","title":"FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion","created":"2024-02-05","cited_by_count":68},{"id":"2305.12281","title":"Lifelong Language Pretraining with Distribution-Specialized Experts","created":"2023-05-20","cited_by_count":66},{"id":"2210.16955","title":"Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles","created":"2022-10-30","cited_by_count":60},{"id":"2404.11565","title":"MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation","created":"2024-04-17","cited_by_count":51},{"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},{"id":"2405.13055","title":"Large Language Models for Medicine: A Survey","created":"2024-05-20","cited_by_count":38},{"id":"2205.10034","title":"MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Services","created":"2022-05-20","cited_by_count":37},{"id":"2310.09832","title":"Merging Experts into One: Improving Computational Efficiency of Mixture of Experts","created":"2023-10-15","cited_by_count":37},{"id":"2306.04073","title":"Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks","created":"2023-06-07","cited_by_count":35},{"id":"2408.10159","title":"Customizing Language Models with Instance-wise LoRA for Sequential Recommendation","created":"2024-08-19","cited_by_count":32},{"id":"2205.15996","title":"Text2Human: Text-Driven Controllable Human Image Generation","created":"2022-05-31","cited_by_count":31},{"id":"2403.04697","title":"AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors","created":"2024-03-07","cited_by_count":29},{"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":"2311.05804","title":"Model-as-a-Service (MaaS): A Survey","created":"2023-11-10","cited_by_count":25},{"id":"2112.04216","title":"Specializing Versatile Skill Libraries using Local Mixture of Experts","created":"2021-12-08","cited_by_count":24},{"id":"2305.18691","title":"Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts","created":"2023-05-30","cited_by_count":23},{"id":"2105.06597","title":"RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling","created":"2021-05-14","cited_by_count":22},{"id":"2404.19429","title":"Lancet: Accelerating Mixture-of-Experts Training via Whole Graph Computation-Communication Overlapping","created":"2024-04-30","cited_by_count":22},{"id":"2305.06324","title":"Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception","created":"2023-05-10","cited_by_count":19},{"id":"2406.11256","title":"Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts","created":"2024-06-17","cited_by_count":19},{"id":"2006.05911","title":"Continuous Action Reinforcement Learning from a Mixture of Interpretable Experts","created":"2020-06-10","cited_by_count":17},{"id":"2202.03881","title":"Robust Hybrid Learning With Expert Augmentation","created":"2022-02-08","cited_by_count":17},{"id":"2208.02894","title":"Redesigning Multi-Scale Neural Network for Crowd Counting","created":"2022-08-04","cited_by_count":17},{"id":"2312.10073","title":"Data Scarcity in Recommendation Systems: A Survey","created":"2023-12-08","cited_by_count":17},{"id":"2310.07188","title":"Adaptive Gating in Mixture-of-Experts based Language Models","created":"2023-10-11","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":"2307.07994","title":"Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach","created":"2023-07-16","cited_by_count":15},{"id":"2403.01197","title":"DMoERM: Recipes of Mixture-of-Experts for Effective Reward Modeling","created":"2024-03-02","cited_by_count":15},{"id":"2407.11245","title":"Pacer and Runner: Cooperative Learning Framework between Single- and Cross-Domain Sequential Recommendation","created":"2024-07-15","cited_by_count":13},{"id":"2205.06532","title":"Addressing Confounding Feature Issue for Causal Recommendation","created":"2022-05-13","cited_by_count":12},{"id":"2211.14952","title":"Federated Learning Attacks and Defenses: A Survey","created":"2022-11-27","cited_by_count":12},{"id":"2105.04181","title":"KDExplainer: A Task-oriented Attention Model for Explaining Knowledge Distillation","created":"2021-05-10","cited_by_count":11},{"id":"2201.01633","title":"Adaptive Online Incremental Learning for Evolving Data Streams","created":"2022-01-05","cited_by_count":11},{"id":"2205.08776","title":"AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation","created":"2022-05-18","cited_by_count":11},{"id":"2304.06032","title":"Web 3.0: The Future of Internet","created":"2023-03-23","cited_by_count":11},{"id":"2004.13999","title":"Privacy-Preserving Distributed Optimization via Subspace Perturbation: A General Framework","created":"2020-04-29","cited_by_count":10},{"id":"2107.04694","title":"Lifelong Mixture of Variational Autoencoders","created":"2021-07-09","cited_by_count":10},{"id":"2205.07851","title":"ST-ExpertNet: A Deep Expert Framework for Traffic Prediction","created":"2022-05-05","cited_by_count":10},{"id":"2302.11875","title":"Improved Training of Mixture-of-Experts Language GANs","created":"2023-02-23","cited_by_count":7},{"id":"2405.04198","title":"Enhancing Physical Layer Communication Security through Generative AI with Mixture of Experts","created":"2024-05-07","cited_by_count":7},{"id":"2407.00599","title":"Parm: Efficient Training of Large Sparsely-Activated Models with Dedicated Schedules","created":"2024-06-30","cited_by_count":7},{"id":"2304.06111","title":"Web3: The Next Internet Revolution","created":"2023-03-22","cited_by_count":6},{"id":"2302.00586","title":"PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Markets","created":"2023-01-14","cited_by_count":5},{"id":"2302.10850","title":"Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management","created":"2023-02-21","cited_by_count":3},{"id":"2407.18581","title":"Dynamic Language Group-Based MoE: Enhancing Code-Switching Speech Recognition with Hierarchical Routing","created":"2024-07-26","cited_by_count":2},{"id":"2007.02432","title":"Extending Mixture of Experts Model to Investigate Heterogeneity of Trajectories: When, Where and How to Add Which Covariates","created":"2020-07-05","cited_by_count":1},{"id":"2203.02384","title":"AutoMO-Mixer: An automated multi-objective Mixer model for balanced, safe and robust prediction in medicine","created":"2022-03-04","cited_by_count":1},{"id":"2211.00558","title":"Contextual Mixture of Experts: Integrating Knowledge into Predictive Modeling","created":"2022-11-01","cited_by_count":1},{"id":"2310.13699","title":"Interaction in Metaverse: A Survey","created":"2023-09-28","cited_by_count":1},{"id":"2408.14700","title":"Artificial Intelligence in Landscape Architecture: A Survey","created":"2024-08-26","cited_by_count":1}],"next_cursor":null}