{"total":18,"rows":[{"id":"2403.19887","title":"Jamba: A Hybrid Transformer-Mamba Language Model","created":"2024-03-28","cited_by_count":401,"area":"moe"},{"id":"2601.07372","title":"Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models","created":"2026-01-12","cited_by_count":86,"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":"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":"2503.05447","title":"Linear-MoE: Linear Sequence Modeling Meets Mixture-of-Experts","created":"2025-03-07","cited_by_count":6,"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":"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":"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":"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":"2501.13994","title":"CSAOT: Cooperative Multi-Agent System for Active Object Tracking","created":"2025-01-23","cited_by_count":0,"area":"moe"},{"id":"2504.08247","title":"Millions of States: Designing a Scalable MoE Architecture with RWKV-7 Meta-learner","created":"2025-04-11","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":"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":"2603.06938","title":"Swimba: Switch Mamba Model Scales State Space Models","created":"2026-03-06","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":"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":"2608.21840","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"}],"next_cursor":null}