{"total":66,"rows":[{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2505.06708","title":"Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free","created":"2025-05-10","cited_by_count":283,"area":"moe"},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237,"area":"moe"},{"id":"2502.13189","title":"MoBA: Mixture of Block Attention for Long-Context LLMs","created":"2025-02-18","cited_by_count":198,"area":"moe"},{"id":"2410.13276","title":"SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs","created":"2024-10-17","cited_by_count":124,"area":"moe"},{"id":"2412.14711","title":"ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing","created":"2024-12-19","cited_by_count":54,"area":"moe"},{"id":"2406.05955","title":"Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters","created":"2024-06-10","cited_by_count":38,"area":"moe"},{"id":"2402.01771","title":"BlackMamba: Mixture of Experts for State-Space Models","created":"2024-02-01","cited_by_count":37,"area":"moe"},{"id":"2410.19034","title":"Mixture of Parrots: Experts improve memorization more than reasoning","created":"2024-10-24","cited_by_count":21,"area":"moe"},{"id":"2507.00029","title":"LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing","created":"2025-06-17","cited_by_count":18,"area":"moe"},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2601.18699","title":"Mechanistic Analysis of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2026-01-26","cited_by_count":14,"area":"moe"},{"id":"2602.03560","title":"HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing","created":"2026-02-03","cited_by_count":10,"area":"moe"},{"id":"2506.07814","title":"M2Restore: Mixture-of-Experts-based Mamba-CNN Fusion Framework for All-in-One Image Restoration","created":"2025-06-09","cited_by_count":7,"area":"moe"},{"id":"2503.05447","title":"Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts","created":"2025-03-07","cited_by_count":6,"area":"moe"},{"id":"2505.07260","title":"UMoE: Unifying Attention and FFN with Shared Experts","created":"2025-05-12","cited_by_count":6,"area":"moe"},{"id":"2505.20001","title":"NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identification","created":"2025-05-26","cited_by_count":6,"area":"moe"},{"id":"2502.05335","title":"Towards Foundational Models for Dynamical System Reconstruction: Hierarchical Meta-Learning via Mixture of Experts","created":"2025-02-07","cited_by_count":5,"area":"moe"},{"id":"2505.17257","title":"JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model","created":"2025-05-22","cited_by_count":5,"area":"moe"},{"id":"2510.04476","title":"Compressed Convolutional Attention: Efficient Attention in a Compressed Latent Space","created":"2025-10-06","cited_by_count":5,"area":"moe"},{"id":"2510.16756","title":"End-to-end Listen, Look, Speak and Act","created":"2025-10-19","cited_by_count":5,"area":"moe"},{"id":"2606.26560","title":"Erase-then-Delta Attention: Decoupling Erase and Write Addresses in Delta-Rule Linear Attention","created":"2026-06-25","cited_by_count":5,"area":"moe"},{"id":"2503.14655","title":"Core-Periphery Principle Guided State Space Model for Functional Connectome Classification","created":"2025-03-18","cited_by_count":4,"area":"moe"},{"id":"2506.18145","title":"Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection","created":"2025-06-22","cited_by_count":4,"area":"moe"},{"id":"2507.15465","title":"Rethinking LLM Inference Bottlenecks: Insights from Latent Attention and Mixture-of-Experts","created":"2025-07-21","cited_by_count":4,"area":"moe"},{"id":"2607.14530","title":"xHC: Expanded Hyper-Connections","created":"2026-07-16","cited_by_count":4,"area":"moe"},{"id":"2504.20509","title":"MambaMoE: Mixture-of-Spectral-Spatial-Experts State Space Model for Hyperspectral Image Classification","created":"2025-04-29","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":"2408.11855","title":"FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models","created":"2024-08-15","cited_by_count":2,"area":"moe"},{"id":"2510.04923","title":"REN: Anatomically-Informed Mixture-of-Experts for Interstitial Lung Disease Diagnosis","created":"2025-10-06","cited_by_count":2,"area":"moe"},{"id":"2412.11834","title":"Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture","created":"2024-12-16","cited_by_count":1,"area":"moe"},{"id":"2511.18534","title":"HiFi-MambaV2: Hierarchical Shared-Routed MoE for High-Fidelity MRI Reconstruction","created":"2025-11-23","cited_by_count":1,"area":"moe"},{"id":"2601.01260","title":"MambaFormer: Token-Level Guided Routing Mixture-of-Experts for Accurate and Efficient Clinical Assistance","created":"2026-01-03","cited_by_count":1,"area":"moe"},{"id":"2602.06862","title":"Parameters as Experts: Adapting Vision Models with Dynamic Parameter Routing","created":"2026-02-06","cited_by_count":1,"area":"moe"},{"id":"2605.17598","title":"Mixture of Experts for Low-Resource LLMs","created":"2026-05-17","cited_by_count":1,"area":"moe"},{"id":"2607.00780","title":"SpiralFovea: Input-Adaptive Foveated Tokenization as a Third Lever of Resource-Adaptive Inference","created":"2026-07-01","cited_by_count":1,"area":"moe"},{"id":"2501.13994","title":"CSAOT: Cooperative Multi-Agent System for Active Object Tracking","created":"2025-01-23","cited_by_count":0,"area":"moe"},{"id":"2502.14788","title":"Ray-Tracing for Conditionally Activated Neural Networks","created":"2025-02-20","cited_by_count":0,"area":"moe"},{"id":"2503.06059","title":"MANDARIN: Mixture-of-Experts Framework for Dynamic Delirium and Coma Prediction in ICU Patients: Development and Validation of an Acute Brain Dysfunction Prediction Model","created":"2025-03-08","cited_by_count":0,"area":"moe"},{"id":"2505.12007","title":"Multi-modal Collaborative Optimization and Expansion Network for Event-assisted Single-eye Expression Recognition","created":"2025-05-17","cited_by_count":0,"area":"moe"},{"id":"2507.17662","title":"Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography","created":"2025-07-23","cited_by_count":0,"area":"moe"},{"id":"2510.26182","title":"MossNet: Mixture of State-Space Experts is a Multi-Head Attention","created":"2025-10-30","cited_by_count":0,"area":"moe"},{"id":"2510.27155","title":"Hierarchical Fusion of Local and Global Visual Features with Mixture-of-Experts for Remote Sensing Image Scene Classification","created":"2025-10-31","cited_by_count":0,"area":"moe"},{"id":"2512.21707","title":"Spatiotemporal-Untrammelled Mixture of Experts for Multi-Person Motion Prediction","created":"2025-12-25","cited_by_count":0,"area":"moe"},{"id":"2512.22741","title":"Text-Routed Sparse Mixture-of-Experts Model with Explanation and Temporal Alignment for Multi-Modal Sentiment Analysis","created":"2025-12-28","cited_by_count":0,"area":"moe"},{"id":"2603.06378","title":"MoEMambaMIL: Structure-Aware Selective State Space Modeling for Whole-Slide Image Analysis","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2603.06938","title":"Swimba: Switch Mamba Model Scales State Space Models","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2603.10031","title":"Architecture-Aware LLM Inference Optimization on AMD Instinct GPUs: A Comprehensive Benchmark and Deployment Study","created":"2026-02-27","cited_by_count":0,"area":"moe"},{"id":"2603.14816","title":"M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts","created":"2026-03-16","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":"2605.00604","title":"Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts","created":"2026-05-01","cited_by_count":0,"area":"moe"},{"id":"2605.09516","title":"Mixture of Layers with Hybrid Attention","created":"2026-05-10","cited_by_count":0,"area":"moe"},{"id":"2605.17719","title":"Patch-MoE Mamba: A Patch-Ordered Mixture-of-Experts State Space Architecture for Medical Image Segmentation","created":"2026-05-18","cited_by_count":0,"area":"moe"},{"id":"2605.18848","title":"Exact Linear Attention","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2607.14568","title":"A Modern Multimodal Assistant on a 6 GB 2011 GPU: Stage-Validated, All-GPU CUDA Inference for Fermi","created":"2026-07-16","cited_by_count":0,"area":"moe"},{"id":"2608.08081","title":"RotaryQuant: Fitting 120B MoE Models on Consumer Hardware via Fused Compressed-Space Attention","created":"2026-08-08","cited_by_count":0,"area":"moe"},{"id":"2608.10947","title":"Mixture-of-Experts-based Entropy Model for Learned Image Compression","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2608.15051","title":"A Unified Mamba--MoE Surrogate for Closed-Loop Simulation and Measurement-Window Forecasting of Inverter Transients","created":"2026-08-15","cited_by_count":0,"area":"moe"},{"id":"2608.17342","title":"MoFE: A Novel Mixture-of-Experts Framework with Fourier Neural Operators for Cryptocurrency Forecasting","created":"2026-08-18","cited_by_count":0,"area":"moe"},{"id":"2608.17744","title":"Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See","created":"2026-08-18","cited_by_count":0,"area":"moe"},{"id":"2608.21840","title":"More Experts, Worse Dynamics: Inverse Scaling and Spectral Bias in Mixture-of-Experts State-Space Models","created":"2026-08-22","cited_by_count":0,"area":"moe"},{"id":"2608.22613","title":"NOVA: Technology-Architecture Co-Design of Near-Memory Processing for Attention-SSM-MoE Hybrid LLM Inference","created":"2026-08-23","cited_by_count":0,"area":"moe"},{"id":"2609.18063","title":"The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction","created":"2026-09-16","cited_by_count":0,"area":"moe"},{"id":"2609.29618","title":"An Exploratory Ablation of a Small MLA--SSM Hybrid Language Model","created":"2026-08-28","cited_by_count":0,"area":"moe"},{"id":"2610.05484","title":"Universal Test-Time Training","created":"2026-10-04","cited_by_count":0,"area":"moe"},{"id":"2610.12495","title":"Kairos: Toward a Byte-Level Foundation Model for Every Modality","created":"2026-09-26","cited_by_count":0,"area":"moe"}],"next_cursor":null}