{"total":51,"rows":[{"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,"area":"moe"},{"id":"2503.07137","title":"A Comprehensive Survey of Mixture-of-Experts: Algorithms, Theory, and Applications","created":"2025-03-10","cited_by_count":91,"area":"moe"},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2405.11157","title":"Towards Modular LLMs by Building and Reusing a Library of LoRAs","created":"2024-05-18","cited_by_count":72,"area":null},{"id":"2402.05859","title":"Learning to Route Among Specialized Experts for Zero-Shot Generalization","created":"2024-02-08","cited_by_count":65,"area":null},{"id":"2408.07057","title":"A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning","created":"2024-08-13","cited_by_count":52,"area":null},{"id":"2303.06182","title":"Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference","created":"2023-03-10","cited_by_count":37,"area":"moe"},{"id":"2309.13850","title":"Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts","created":"2023-09-25","cited_by_count":29,"area":"moe"},{"id":"2310.09762","title":"Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer","created":"2023-10-15","cited_by_count":29,"area":"moe"},{"id":"2402.12550","title":"Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization","created":"2024-02-19","cited_by_count":28,"area":"moe"},{"id":"2408.11304","title":"FedMoE: Personalized Federated Learning via Heterogeneous Mixture of Experts","created":"2024-08-21","cited_by_count":27,"area":"moe"},{"id":"2405.13997","title":"Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts","created":"2024-05-22","cited_by_count":24,"area":"moe"},{"id":"2310.14188","title":"A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts","created":"2023-10-22","cited_by_count":23,"area":"moe"},{"id":"2402.02952","title":"On Least Square Estimation in Softmax Gating Mixture of Experts","created":"2024-02-05","cited_by_count":23,"area":"moe"},{"id":"2406.18420","title":"Mixture of Experts in a Mixture of RL settings","created":"2024-06-26","cited_by_count":21,"area":"moe"},{"id":"2312.10868","title":"From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape","created":"2023-12-18","cited_by_count":18,"area":"moe"},{"id":"2306.04640","title":"ModuleFormer: Modularity Emerges from Mixture-of-Experts","created":"2023-06-07","cited_by_count":17,"area":"moe"},{"id":"2310.09163","title":"Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN","created":"2023-10-13","cited_by_count":15,"area":null},{"id":"2406.20030","title":"LEMoE: Advanced Mixture of Experts Adaptor for Lifelong Model Editing of Large Language Models","created":"2024-06-28","cited_by_count":14,"area":"moe"},{"id":"2205.12701","title":"Eliciting and Understanding Cross-Task Skills with Task-Level Mixture-of-Experts","created":"2022-05-25","cited_by_count":12,"area":"moe"},{"id":"2410.14574","title":"MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts","created":"2024-10-18","cited_by_count":9,"area":"moe"},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2402.15082","title":"PEMT: Multi-Task Correlation Guided Mixture-of-Experts Enables Parameter-Efficient Transfer Learning","created":"2024-02-23","cited_by_count":7,"area":"moe"},{"id":"2406.05360","title":"Flexible and Adaptable Summarization via Expertise Separation","created":"2024-06-08","cited_by_count":7,"area":null},{"id":"2410.07172","title":"Glider: Global and Local Instruction-Driven Expert Router","created":"2024-10-09","cited_by_count":4,"area":null},{"id":"2502.11513","title":"MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2503.02152","title":"Tabby: A Language Model Architecture for Tabular and Structured Data Synthesis","created":"2025-03-04","cited_by_count":4,"area":"synth"},{"id":"2503.03213","title":"Convergence Rates for Softmax Gating Mixture of Experts","created":"2025-03-05","cited_by_count":4,"area":"moe"},{"id":"2303.04338","title":"Provable Pathways: Learning Multiple Tasks over Multiple Paths","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2406.15883","title":"SimSMoE: Solving Representational Collapse via Similarity Measure","created":"2024-06-22","cited_by_count":3,"area":"moe"},{"id":"2306.11027","title":"JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving","created":"2023-06-19","cited_by_count":2,"area":"lr"},{"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":"2407.01126","title":"Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation","created":"2024-07-01","cited_by_count":1,"area":"moe"},{"id":"2508.16937","title":"NAT: Learning to Attack Neurons for Enhanced Adversarial Transferability","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2605.09355","title":"FLAME: Adaptive Mixture-of-Experts for Continual Multimodal Multi-Task Learning","created":"2026-05-10","cited_by_count":1,"area":"wm"},{"id":"2306.16176","title":"SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2310.10480","title":"G-SPEED: General SParse Efficient Editing MoDel","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2412.17364","title":"Efficient fine-tuning methodology of text embedding models for information retrieval: contrastive learning penalty (clp)","created":"2024-12-23","cited_by_count":0,"area":null},{"id":"2501.08057","title":"Optimizing Speech Multi-View Feature Fusion through Conditional Computation","created":"2025-01-14","cited_by_count":0,"area":null},{"id":"2508.10009","title":"Beyond Hard Sharing: Efficient Multi-Task Speech-to-Text Modeling with Supervised Mixture of Experts","created":"2025-08-05","cited_by_count":0,"area":"moe"},{"id":"2509.08032","title":"SciGPT: A Large Language Model for Scientific Literature Understanding and Knowledge Discovery","created":"2025-09-09","cited_by_count":0,"area":"moe"},{"id":"2509.08470","title":"Joint Learning using Mixture-of-Expert-Based Representation for Speech Enhancement and Robust Emotion Recognition","created":"2025-09-10","cited_by_count":0,"area":"moe"},{"id":"2604.03342","title":"Mixture-of-Experts in Remote Sensing: A Survey","created":"2026-04-03","cited_by_count":0,"area":"moe"},{"id":"2604.18866","title":"HMR-Net: Hierarchical Modular Routing for Cross-Domain Object Detection in Aerial Images","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.05891","title":"MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors","created":"2026-05-07","cited_by_count":0,"area":"moe"},{"id":"2606.01784","title":"MoRE: A Mixture-of-Experts-Based Task-Adaptive End-to-End Network for Multimodal MRI Reconstruction","created":"2026-06-01","cited_by_count":0,"area":"moe"},{"id":"2606.16456","title":"SPRI: SVD-Partitioned Residual Initialization for Data-Constrained MoE Upcycling","created":"2026-06-15","cited_by_count":0,"area":"moe"},{"id":"2608.21878","title":"ViSMoE: Visual-Aware Sparse Mixture-of-Experts for Embodied Referring Expression Grounding","created":"2026-08-22","cited_by_count":0,"area":"moe"}],"next_cursor":null}