{"total":32,"rows":[{"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":"2512.23447","title":"Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss","created":"2025-12-29","cited_by_count":11,"area":"moe"},{"id":"2508.02853","title":"Modeling Annotator Disagreement with Demographic-Aware Experts and Synthetic Perspectives","created":"2025-08-04","cited_by_count":10,"area":"moe"},{"id":"2511.10971","title":"ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization","created":"2025-11-14","cited_by_count":7,"area":"moe"},{"id":"2602.14159","title":"Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization","created":"2026-02-15","cited_by_count":5,"area":"moe"},{"id":"2605.15403","title":"$\\phi$-Balancing for Mixture-of-Experts Training","created":"2026-05-14","cited_by_count":5,"area":"moe"},{"id":"2602.00509","title":"PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching","created":"2026-01-31","cited_by_count":4,"area":"moe"},{"id":"2605.06663","title":"EMO: Pretraining Mixture of Experts for Emergent Modularity","created":"2026-05-07","cited_by_count":4,"area":"moe"},{"id":"2605.12476","title":"Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts","created":"2026-05-12","cited_by_count":4,"area":"moe"},{"id":"2601.03577","title":"Variational Inference, Entropy, and Orthogonality: A Unified Theory of Mixture-of-Experts","created":"2026-01-07","cited_by_count":3,"area":"moe"},{"id":"2602.12556","title":"SD-MoE: Spectral Decomposition for Effective Expert Specialization","created":"2026-02-13","cited_by_count":3,"area":"moe"},{"id":"2509.06346","title":"Ban&Pick: Enhancing Performance and Efficiency of MoE-LLMs via Smarter Routing","created":"2025-09-08","cited_by_count":2,"area":"moe"},{"id":"2601.12137","title":"EMoE: Eigenbasis-Guided Routing for Mixture-of-Experts","created":"2026-01-17","cited_by_count":2,"area":"moe"},{"id":"2511.16947","title":"Fine-grained MoE Load Balancing with Linear Programming","created":"2025-11-21","cited_by_count":1,"area":"moe"},{"id":"2601.21547","title":"Multi-Modal Time Series Prediction via Mixture of Modulated Experts","created":"2026-01-29","cited_by_count":1,"area":"moe"},{"id":"2604.07030","title":"MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale","created":"2026-04-08","cited_by_count":1,"area":"moe"},{"id":"2605.25166","title":"AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting","created":"2026-05-24","cited_by_count":1,"area":"moe"},{"id":"2606.20544","title":"Toward Calibrated Mixture-of-Experts Under Distribution Shift","created":"2026-06-18","cited_by_count":1,"area":"moe"},{"id":"2606.26183","title":"LiMoDE: Rethinking Lifelong Robot Manipulation from a Mixture-of-Dynamic-Experts Perspective","created":"2026-06-24","cited_by_count":1,"area":"moe"},{"id":"2512.22296","title":"Hybrid Quantum-Classical Mixture of Experts: Unlocking Topological Advantage via Interference-Based Routing","created":"2025-12-25","cited_by_count":0,"area":"moe"},{"id":"2602.14039","title":"Geometry-Preserving Aggregation for Mixture-of-Experts Embedding Models","created":"2026-02-15","cited_by_count":0,"area":"moe"},{"id":"2604.05267","title":"Do Domain-specific Experts exist in MoE-based LLMs?","created":"2026-04-07","cited_by_count":0,"area":"moe"},{"id":"2604.13508","title":"Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling","created":"2026-04-15","cited_by_count":0,"area":"moe"},{"id":"2604.14500","title":"Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection","created":"2026-04-16","cited_by_count":0,"area":"moe"},{"id":"2604.23740","title":"Transformer as an Euler Discretization of Score-based Variational Flow","created":"2026-04-26","cited_by_count":0,"area":"moe"},{"id":"2605.06415","title":"E = T*H/(O+B): A Dimensionless Control Parameter for Mixture-of-Experts Ecology","created":"2026-05-07","cited_by_count":0,"area":"moe"},{"id":"2606.25665","title":"Learning Subset-Shared Invariances for Domain Generalization with Mixture-of-Experts","created":"2026-06-24","cited_by_count":0,"area":"moe"},{"id":"2608.06396","title":"TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation","created":"2026-07-31","cited_by_count":0,"area":"moe"},{"id":"2608.10392","title":"Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation","created":"2026-08-11","cited_by_count":0,"area":"moe"},{"id":"2609.08115","title":"Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training","created":"2026-09-08","cited_by_count":0,"area":"moe"},{"id":"2609.32398","title":"Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism","created":"2026-09-26","cited_by_count":0,"area":"moe"},{"id":"2610.05744","title":"CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training","created":"2026-10-05","cited_by_count":0,"area":"moe"}],"next_cursor":null}