{"total":98,"rows":[{"id":"2210.17223","title":"Accelerating Distributed MoE Training and Inference with Lina","created":"2022-10-31","cited_by_count":109,"area":"moe"},{"id":"2310.01334","title":"Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy","created":"2023-10-02","cited_by_count":108,"area":"moe"},{"id":"2402.08609","title":"Mixtures of Experts Unlock Parameter Scaling for Deep RL","created":"2024-02-13","cited_by_count":78,"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":"2403.17749","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","created":"2024-03-26","cited_by_count":58,"area":"moe"},{"id":"2407.01531","title":"Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning","created":"2024-07-01","cited_by_count":57,"area":"diffusion"},{"id":"2412.14219","title":"A Survey on Inference Optimization Techniques for Mixture of Experts Models","created":"2024-12-18","cited_by_count":47,"area":"moe"},{"id":"2404.01260","title":"Bridging Remote Sensors with Multisensor Geospatial Foundation Models","created":"2024-04-01","cited_by_count":46,"area":null},{"id":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45,"area":"moe"},{"id":"2405.14124","title":"Mixture of Experts Meets Prompt-Based Continual Learning","created":"2024-05-23","cited_by_count":43,"area":"moe"},{"id":"2310.18859","title":"SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models","created":"2023-10-29","cited_by_count":38,"area":"moe"},{"id":"2305.03288","title":"Demystifying Softmax Gating Function in Gaussian Mixture of Experts","created":"2023-05-05","cited_by_count":33,"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":"2308.11793","title":"Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts","created":"2023-08-22","cited_by_count":27,"area":"moe"},{"id":"2308.15030","title":"SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget","created":"2023-08-29","cited_by_count":27,"area":"moe"},{"id":"2312.00968","title":"Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts","created":"2023-12-01","cited_by_count":26,"area":"mllm"},{"id":"2302.02596","title":"Ten Lessons We Have Learned in the New \"Sparseland\": A Short Handbook for Sparse Neural Network Researchers","created":"2023-02-06","cited_by_count":25,"area":null},{"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":"2503.02891","title":"Vision Transformers on the Edge: A Comprehensive Survey of Model Compression and Acceleration Strategies","created":"2025-02-26","cited_by_count":24,"area":null},{"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,"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":"2410.07265","title":"A Survey: Collaborative Hardware and Software Design in the Era of Large Language Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2403.20022","title":"Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity","created":"2024-03-29","cited_by_count":22,"area":"moe"},{"id":"2410.19123","title":"Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design","created":"2024-10-24","cited_by_count":19,"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":"2403.15389","title":"DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data","created":"2024-03-22","cited_by_count":18,"area":"diffusion"},{"id":"2501.16352","title":"Mixture of Experts (MoE): A Big Data Perspective","created":"2025-01-18","cited_by_count":18,"area":"moe"},{"id":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17,"area":null},{"id":"2405.14131","title":"Statistical Advantages of Perturbing Cosine Router in Mixture of Experts","created":"2024-05-23","cited_by_count":16,"area":"moe"},{"id":"2504.03166","title":"RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation","created":"2025-04-04","cited_by_count":16,"area":"moe"},{"id":"2212.08066","title":"Mod-Squad: Designing Mixture of Experts As Modular Multi-Task Learners","created":"2022-12-15","cited_by_count":15,"area":"moe"},{"id":"2401.13875","title":"Is Temperature Sample Efficient for Softmax Gaussian Mixture of Experts?","created":"2024-01-25","cited_by_count":15,"area":"moe"},{"id":"2505.24378","title":"Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer","created":"2025-05-30","cited_by_count":15,"area":"moe"},{"id":"2406.09679","title":"Exploring Training on Heterogeneous Data with Mixture of Low-rank Adapters","created":"2024-06-14","cited_by_count":12,"area":null},{"id":"2410.07901","title":"Semi-Supervised Video Desnowing Network via Temporal Decoupling Experts and Distribution-Driven Contrastive Regularization","created":"2024-10-10","cited_by_count":11,"area":null},{"id":"2405.16486","title":"Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation","created":"2024-05-26","cited_by_count":10,"area":"moe"},{"id":"2406.04801","title":"MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks","created":"2024-06-07","cited_by_count":9,"area":"moe"},{"id":"2410.05357","title":"Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild","created":"2024-10-07","cited_by_count":9,"area":null},{"id":"2310.00986","title":"Multi-task Learning with 3D-Aware Regularization","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2410.14633","title":"Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning","created":"2024-10-18","cited_by_count":7,"area":null},{"id":"2404.01976","title":"Joint-Task Regularization for Partially Labeled Multi-Task Learning","created":"2024-04-02","cited_by_count":6,"area":null},{"id":"2411.00918","title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","created":"2024-11-01","cited_by_count":6,"area":"moe"},{"id":"2304.08594","title":"AdaMTL: Adaptive Input-dependent Inference for Efficient Multi-Task Learning","created":"2023-04-17","cited_by_count":5,"area":null},{"id":"2312.16610","title":"Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation","created":"2023-12-27","cited_by_count":5,"area":"moe"},{"id":"2507.07778","title":"Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2510.15338","title":"Proto-Former: Unified Facial Landmark Detection by Prototype Transformer","created":"2025-10-17","cited_by_count":5,"area":null},{"id":"2307.07742","title":"SINC: Self-Supervised In-Context Learning for Vision-Language Tasks","created":"2023-07-15","cited_by_count":4,"area":null},{"id":"2405.10951","title":"Block Selective Reprogramming for On-device Training of Vision Transformers","created":"2024-03-25","cited_by_count":4,"area":"moe"},{"id":"2408.15388","title":"Panoptic Perception for Autonomous Driving: A Survey","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2502.05602","title":"UbiMoE: A Ubiquitous Mixture-of-Experts Vision Transformer Accelerator With Hybrid Computation Pattern on FPGA","created":"2025-02-08","cited_by_count":4,"area":"moe"},{"id":"2503.03213","title":"Convergence Rates for Softmax Gating Mixture of Experts","created":"2025-03-05","cited_by_count":4,"area":"moe"},{"id":"2507.07485","title":"Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2510.13451","title":"Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts","created":"2025-10-15","cited_by_count":4,"area":"safety"},{"id":"2505.15414","title":"Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks","created":"2025-05-21","cited_by_count":3,"area":"moe"},{"id":"2507.06363","title":"Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation","created":"2025-07-08","cited_by_count":3,"area":"moe"},{"id":"2509.23915","title":"Revisit the Imbalance Optimization in Multi-task Learning: An Experimental Analysis","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2510.00570","title":"Adaptive Shared Experts with LoRA-Based Mixture of Experts for Multi-Task Learning","created":"2025-10-01","cited_by_count":3,"area":"moe"},{"id":"2402.05220","title":"On Parameter Estimation in Deviated Gaussian Mixture of Experts","created":"2024-02-07","cited_by_count":2,"area":"moe"},{"id":"2402.07334","title":"Differentially Private Training of Mixture of Experts Models","created":"2024-02-11","cited_by_count":2,"area":"moe"},{"id":"2503.08006","title":"Injecting Imbalance Sensitivity for Multi-Task Learning","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2506.08013","title":"StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets","created":"2025-06-09","cited_by_count":2,"area":"diffusion"},{"id":"2510.12744","title":"Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency Without Model Sweeps","created":"2025-10-14","cited_by_count":2,"area":"moe"},{"id":"2511.20646","title":"3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2602.10659","title":"Multimodal Priors-Augmented Text-Driven 3D Human-Object Interaction Generation","created":"2026-02-11","cited_by_count":2,"area":"moe"},{"id":"2402.16848","title":"InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2410.15732","title":"ViMoE: An Empirical Study of Designing Vision Mixture-of-Experts","created":"2024-10-21","cited_by_count":1,"area":"moe"},{"id":"2411.01288","title":"Hexa-MoE: Efficient and Heterogeneous-aware Training for Mixture-of-Experts","created":"2024-11-02","cited_by_count":1,"area":"moe"},{"id":"2412.10028","title":"Mr. DETR++: Instructive Multi-Route Training for Detection Transformers with Mixture-of-Experts","created":"2024-12-13","cited_by_count":1,"area":"moe"},{"id":"2505.18455","title":"On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts","created":"2025-05-24","cited_by_count":1,"area":"moe"},{"id":"2506.06830","title":"EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2507.07883","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2507.19077","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","created":"2025-07-25","cited_by_count":1,"area":"moe"},{"id":"2512.20420","title":"Simplifying Multi-Task Architectures Through Task-Specific Normalization","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2601.10921","title":"RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2412.00316","title":"HiMoE: Heterogeneity-Informed Mixture-of-Experts for Fair Spatial-Temporal Forecasting","created":"2024-11-30","cited_by_count":0,"area":"moe"},{"id":"2412.17009","title":"Expert Routing with Synthetic Data for Continual Learning","created":"2024-12-22","cited_by_count":0,"area":"moe"},{"id":"2501.06884","title":"Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning","created":"2025-01-12","cited_by_count":0,"area":"moe"},{"id":"2506.08496","title":"CoQMoE: Co-Designed Quantization and Computation Orchestration for Mixture-of-Experts Vision Transformer on FPGA","created":"2025-06-10","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":"2511.14503","title":"Parameter Aware Mamba Model for Multi-task Dense Prediction","created":"2025-11-18","cited_by_count":0,"area":"ssm"},{"id":"2601.07474","title":"Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2602.01466","title":"Rethinking Multinomial Logistic Mixture of Experts with Sigmoid Gating Function","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2602.10254","title":"Area-Efficient In-Memory Computing for Mixture-of-Experts via Multiplexing and Caching","created":"2026-02-10","cited_by_count":0,"area":"moe"},{"id":"2602.20911","title":"From Isolation to Integration: Building an Adaptive Expert Forest for Pre-Trained Model-based Class-Incremental Learning","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.06746","title":"ButterflyViT: 354$\\times$ Expert Compression for Edge Vision Transformers","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2603.23668","title":"Energy Efficient Software Hardware CoDesign for Machine Learning: From TinyML to Large Language Models","created":"2026-03-24","cited_by_count":0,"area":null},{"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":"2605.03348","title":"Toward Structural Multimodal Representations: Specialization, Selection, and Sparsification via Mixture-of-Experts","created":"2026-05-05","cited_by_count":0,"area":"moe"},{"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":"2607.06109","title":"RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations","created":"2026-07-07","cited_by_count":0,"area":"moe"},{"id":"2607.16562","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","created":"2026-07-18","cited_by_count":0,"area":"moe"},{"id":"2608.24372","title":"Bridging Adversarial and Collaborative Learning for AI-Generated Image Quality Assessment","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.24763","title":"MoTE: Mixture of Task Experts for Multi-Task Video Understanding","created":"2026-08-25","cited_by_count":0,"area":"moe"},{"id":"2608.28078","title":"Task-State Adaptation with Prototype Memory for Multi-Task Dense Prediction","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.21346","title":"IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts","created":"2026-09-18","cited_by_count":0,"area":"moe"}],"next_cursor":null}